Probabilistic Logic Networks in a Nutshell

Size: px
Start display at page:

Download "Probabilistic Logic Networks in a Nutshell"

Transcription

1 Probabilistic Logic Networks in a Nutshell Matthew Ikle 1 1 Adams State College, Alamosa CO Abstract. We begin with a brief overview of Probabilistic Logic Networks, distinguish PLN from other approaches to reasoning under uncertainty, and describe some of the main conceptual foundations and goals of PLN. We summarize how knowledge is represented within PLN and describe the four basic truth-value types. We describe a few basic firstorder inference rules and formulas, outline PLN s approach to handling higher-order inference via reduction to first-order rules, and follow this by a brief summary of PLN s handling of quantifiers. Since PLN was and continues to be developed as one of several major components of a broader and more general artificial intelligence project, we next describe the OpenCog project and PLN s roles within the project. Keywords: probabilistic logic, probabilistic networks, artificial general intelligence, PLN, OpenCog 1 Introduction: What is PLN? First introduced as a probabilistic reasoning system within the Webmind Artificial Intelligence project by Ben Goertzel and the late Jeff Pressing, the Probabilistic Logic Networks (PLN) system has evolved and grown considerably. PLN now serves as the probabilistic reasoning system within the open source OpenCog AI engine[7], which has replaced Webmind. The primary focus of PLN is to serve as a systematic, comprehensive, and pragmatic system to manage uncertainty: to handle and reason about imprecise, uncertain, incomplete, and inconsistent data, and reasoning involving uncertain conclusions. Perhaps one of PLN s most striking characteristics is its dual nature. Designed as part of a broader artificial intelligence system, PLN is very practical, encompassing heuristic approaches as necessary. At the same time, considerable effort has been made to ground as much of PLN as possible upon solid theoretical and mathematical foundations. A result of this duality is the following list of desired characteristics: PLN should enable uncertainty-savvy versions of all known varieties of logical reasoning: including, for instance, higher-order reasoning involving quantifiers, higher-order functions, and so forth; PLN should reduce to crisp theorem prover style behavior in the limiting case where uncertainty tends to zero; PLN should encompass inductive and abductive as well as deductive reasoning;

2 2 Probabilistic Logic Networks PLN should agree with probability theory in those reasoning case where probability in its current state of development provides solutions within reasonable calculational effort based on assumptions that are plausible in the context of real-world embodied software systems; PLN should gracefully incorporate heuristics not explicitly based on probability theory, in cases where probability theory, at its current state of development, does not provide adequate pragmatic solutions; PLN should provide scalable reasoning, in the sense of being able to carry out inferences involving at least billions of premises and carry out more intensive and accurate reasoning when the number of premises is fewer; PLN should easily accept input from, and send input to, natural language processing software systems. 2 Relationship of PLN to Other Uncertain Inference Engines It is clear that uncertain inference is hardly a new idea. What is new within PLN is its focus on bridging the theoretical and practical, and how it incorporates and integrates ideas from a variety of sources. PLN borrows heavily upon other approaches to uncertain inference and in many ways represents an amalgam of a large number of these ideas, including such standard approaches as Bayesian probability theory, and fuzzy logic, as well as from more unusual ideas including Pei Wang s Non-Axiomatic Reasoning System (NARS)[12], algorithmic information theory, and Walley s theory of imprecise probabilities[11]. One of the key differences between PLN and other approaches to probabilistic logic lies in PLN s foundation upon term logic. As we shall see later, this foundational choice allows one to reduce PLN s higher-order inference rules to more basic first-order rules. Overall, PLN owes the most to Pei Wang s NARS system and Walley s theory of imprecise probabilities. Pei Wang pioneered the use of uncertain term logic in his NARS system, and in large measure provided the motivation for the development of PLN. Indeed PLN began as part of a collaboration with Wang as an attempt to create a probabilistic analogue to NARS, though there remain many conceptual and mathematical differences between the two, and PLN has long ago diverged from these roots. Peter Walley s theory of imprecise probabilities provided motivation for the development of our indefinite probabilities approach. Essentially a hybridization of Walley s imprecise probabilities with Bayesian credible intervals, indefinite probabilities provide a general and mathematically sound method for calculating the weight-of-evidence underlying the conclusions of uncertain inferences. Moreover, both Walley s imprecise beta-binomial model and standard Bayesian inference can be mathematically viewed as limiting cases of the indefinite probability model. Of the wide array of uncertain inference methods, Bayes nets represent perhaps the most similar approach to PLN, although the graph structures themselves are quite dissimilar. While both methods succeed at embodying probability

3 Probabilistic Logic Networks 3 theory in a set of date structures and algorithms, PLN was designed with different purposes in mind. As a pragmatic approach with an eye towards interaction with an integrative artificial intelligence system, PLN was designed to interface with other cognitive processes and with other kinds of inference, including intensional inference, fuzzy inference, and higher-order inference using quantifiers, variables, and combinators. While PLN utilizes fuzzy set membership as the semantics for Member relationship truth-values, it maintains a clear distinction between uncertainty and partial membership. For many of the purposes commonly associated with fuzzy membership, PLN uses intensional probabilities, giving the advantage of keeping more things within a probabilistic framework. 3 Knowledge Representation within PLN Declarative knowledge representation within PLN is handled by a weighted labeled hypergraph called the Atomspace, which consists of multiple types of nodes and links, generally weighted with probabilistic truth values and attention values PLN is divided into first-order and higher-order sub-theories (FOPLN and HOPLN). These terms are used in a nonstandard way drawn from NARS. We develop FOPLN first, and then derive HOPLN therefrom. FOPLN is a term logic, involving terms and relationships (links) between terms. It is an uncertain logic, in the sense that both terms and relationships are associated with truth value objects, which may come in multiple varieties ranging from single numbers to complex structures like indefinite probabilities[3]. Terms may be either elementary observations, or abstract tokens drawn from a token-set T. 3.1 Core FOPLN Relationships Core FOPLN involves relationships drawn from the set: negation; Inheritance and probabilistic conjunction and disjunction; Member and fuzzy conjunction and disjunction. Elementary observations can have only Member links, while token terms can have any kinds of links. PLN makes clear distinctions, via link type semantics, between probabilistic relationships and fuzzy set relationships. Member semantics are usually fuzzy relationships (though they can also be crisp), whereas Inheritance relationships are probabilistic, and there are rules governing the interoperation of the two types. 3.2 Auxiliary FOPLN Relationships Beyond the core FOPLN relationships, FOPLN involves additional relationship types of two varieties. There are simple ones like Similarity, defined by Similarity A B We say a relationship R is simple if the truth value of R A B can be calculated in terms of the truth values of core FOPLN relationships between A and B.

4 4 Probabilistic Logic Networks There are also complex ones like IntensionalInheritance, which measures the extensional inheritance between the set of properties or patterns associated with one term and the corresponding set associated with another. 3.3 PLN Truth Values Truth-values come in four basic types. In order of increasingly information about the full probability distribution they are strength truth-values, which consist of single numbers; e.g., < s > or <.8 >. Usually strength values denote probabilities but this is not always the case. SimpleTruthValues, consisting of pairs of numbers. These pairs come in two forms: < s, w >, where s is a strength and w is a weight of evidence and < s, N >, where N is a count. Weight of evidence is a qualitative measure of belief, while count is a quantitative measure of accumulated evidence. IndefiniteTruthValues, which quantify truth-values in terms of an interval [L, U], a credibility level b, and an integer k (called the lookahead). IndefiniteTruthValues quantify the idea that after k more observations there is a probability b that the conclusion of the inference will appear to lie in [L, U]. See [3] for more details. DistributionalTruthValues, which are discretized approximations to entire probability distributions. This gradation of truth-value types serves several purposes. Strength and Simple truth values can be used when speed is of the essence or when one simply has little information. When accuracy is most important and when we have additional information concerning an Atom s full probability distribution, then Indefinite and Distributional truth values may be more pertinent. 3.4 PLN Rules and Formulas A distinction is made in PLN between rules and formulas. PLN logical inferences take the form of syllogistic rules, which give patterns for combining statements with matching terms. Examples of PLN rules include, but are not limited to, are the deduction ((A B) (B C) (A C)), induction ((A B) (A C) (B C)), abduction ((A C) (B C) (A C)), inversion rules ((A B) (B A)). Related to each rule is a formula which calculates the truth value resulting from application of the rule. As an example, suppose s A, s B, s C, s AB, and s BC represent the truth values for the terms A, B, C, as well the truth values of the relationships A B and B C, respectively. Then, under suitable conditions imposed upon these input truth values, the formula for the deduction rule is given by: s AC = s AB s BC + (1 s AB) (s C s B s BC ) 1 s B,

5 Probabilistic Logic Networks 5 where s AC represents the truth value of the relationship A C. This formula is directly derived from probability theory given the assumption that A B and B C are independent. Using a combination of probability theory and heuristics, PLN also effectively handles cases in which independence is not a valid assumption. 4 Higher-Order PLN Higher-order PLN (HOPLN) is defined as the subset of PLN that applies to predicates (considered as functions mapping arguments into truth values). It includes mechanisms for dealing with variable-bearing expressions and higherorder functions. A predicate, in PLN, is a special kind of term that embodies a function mapping terms or relationships into truth-values. HOPLN contains several relationships that act upon predicates including Evaluation, Implication, and several types of quantifiers. The relationships can involve constant terms, variables, or a mixture. PLN supports a variety of quantifiers, including traditional crisp and fuzzy quantifiers, plus the AverageQuantifier defined so that the truth value of AverageQuantifier X F (X) is a weighted average of F (X) over all relevant inputs X [3]. AverageQuantifier is used implicitly in PLN to handle logical relationships between predicates, so that e.g. the conclusion of the above deduction is implicitly interpreted as AverageQuantifier X Implication Evaluation is Fluffy X Evaluation is cat X 4.1 Reducing HOPLN to FOPLN In [3] it is shown that in principle, over any finite observation set, HOPLN reduces to FOPLN. The key ideas of this reduction are the elimination of variables via use of higher-order functions, and the use of the set-theoretic definition of function embodied in the SatisfyingSet operator to map function-argument relationships into set-member relationships. As an example, consider the Implication link. In HOPLN, where X is a variable Implication R 1 A X R 2 B X

6 6 Probabilistic Logic Networks may be reduced to Inheritance SatisfyingSet(R 1 A X) SatisfyingSet(R 2 B X) where e.g. SatisfyingSet(R 1 A X) is the fuzzy set of all X satisfying the relationship R 1 (A, X). 5 PLN and AI While PLN serves as a standalone system, recall that PLN grew out of a desire to build an uncertain reasoning module for use within a more general artificial intelligence framework. In order to completely understand many of the open research problems within PLN, it helps to understand the roles PLN plays within this larger context. To address this issue, we examine PLN from two additional viewpoints. First as PLN relates to intelligent agents, and then we will provide an overview of how PLN fits into the larger OpenCog framework. 5.1 SRAM Here we very briefly review a simple formal model of intelligent agents called SRAM, for Simple Realistic Agent Model. Following a theoretical framework developed by Legg and Hutter[8], we consider a class of active agents which observe and explore their environment and also take actions in it, which may affect the environment. The agent sends information to the environment and the environment sends signals to the agent. Agents can also experience rewards. To this framework, we add a set M of memory actions which allow agents to maintain memories (of finite size), and at each time step to carry out internal actions on their memories as well as external actions in the environment. We also introduce the notions of goals and consider the environment as sending goalsymbols to the agent along with regular observation-symbols. In this extended framework, an interaction sequence looks like m 1 a 1 o 1 g 1 r 1 m 2 a 2 o 2 g 2 r 2... where the m i s represent memory actions, the a i s represent external actions, the o i s represent observations, the g i s represent agent goals, and the r i s represent rewards. It is assumed that the reward r i provided to an agent at time i is determined by the goal function g i. If w is introduced as a single symbol to denote the combination of a memory action and an external action, and y is introduced as a single symbol to denote the combination of an observation, a goal and a reward, we can simplify this interaction sequence as w 1 y 1 w 2 y 2...

7 Probabilistic Logic Networks 7 Each goal function maps each finite interaction sequence I g,s,t = wy s:t with g s corresponding to g, into a value r g (I g,s,t ) [0, 1] indicating the value or raw reward of achieving the goal during that interaction sequence. The total reward r t obtained by the agent is the sum of the raw rewards obtained at time t from all goals whose symbols occur in the agent s history before t. The agent is represented as a function π which takes the current history as input, and produces an action as output. Agents need not be deterministic, an agent may for instance induce a probability distribution over the space of possible actions, conditioned on the current history. In this case we may characterize the agent by a probability distribution π(w t wy <t ). Similarly, the environment may be characterized by a probability distribution µ(y k wy <k ). Taken together, the distributions π and µ define a probability measure over the space of interaction sequences. Following Legg and Hutter, we will consider the class of environments that are reward-summable, meaning that the total amount of reward they return to any agent is bounded by 1. We will also use the term context to denote the combination of an environment, a goal function and a reward function. If the agent is acting in environment µ, and is provided with g t = g for the time-interval T = t {t 1,..., t 2 }, then the expected goal-achievement of the agent during the interval is V π µ,g,t t 2 r i t 1 where E is the space of computable, reward-summable environments. Next, we introduce a second-order probability distribution ν, which is a probability distribution over the space of environments µ. The distribution ν assigns each environment a probability. What is key in the above formalism is that this second-order probability distribution ties in nicely with the indefinite probabilities framework and allows us to ground a form of possible worlds semantics within experiential semantics. An agent, experiencing a single stream of perceptions, may use this to construct an ensemble of simulated possible worlds, which may then be used in various sorts of inferences using a commonplace idea in the field of statistics: subsampling, a form of bootstrapping. This notion ties in closely with SRAM, which considers a probability distribution over a space of environments which are themselves probability distributions. What a real agent has is actually a single series of remembered observations. But it can induce a hopeful approximation of this distribution over environments by subsampling its memory and asking: what would it imply about the world if the items in this subsample were the only things I d seen?

8 8 Probabilistic Logic Networks 5.2 PLN s Relationship to OpenCog Now we briefly describe the OCP (OCP) AGI architecture, implemented within the open-source OpenCog AI framework. OCP combines multiple AI paradigms such as uncertain logic, computational linguistics, evolutionary program learning and connectionist attention allocation in a unified architecture. Cognitive processes embodying these different paradigms interoperate together on a common neural-symbolic knowledge store called the Atomspace. The interaction of these processes is designed to encourage the self-organizing emergence of highlevel network structures in the Atomspace, including superposed hierarchical and heterarchical knowledge networks, and a self-model network enabling metaknowledge and meta-learning. The high-level architecture of OCP involves the use of multiple cognitive processes associated with multiple types of memory to enable an intelligent agent to execute the procedures that it believes have the best probability of working toward its goals in its current context. OCP handles low-level perception and action via an extension called OpenCogBot, which integrates a hierarchical temporal memory system, DeSTIN [1]. OCP s memory types are the declarative, procedural, sensory, and episodic memory types that are widely discussed in cognitive neuroscience [10], plus attentional memory for allocating system resources generically, and intentional memory for allocating system resources in a goal-directed way. Table 1 overviews these memory types, giving key references and indicating the corresponding cognitive processes, and also indicating which of the generic patternist cognitive dynamics each cognitive process corresponds to (pattern creation, association, etc.). 6 Conclusion and Future Research Directions The OpenCog software (with PLN as it core reasoning system) has been used for commercial applications in the area of natural language processing and data mining [5]. A collaboration between Novamente LLC and The Electric Sheep Company demonstrated an OpenCog-controlled virtual dog in a virtual world, that can learn new tricks via imitative and reinforcement learning[4] (see http: //novamente.net/example for some videos of these virtual dogs in action). More recently, a new project based at Hong Kong Polytechnic University called M-Lab will explore the creation of generally intelligent humanoid game characters, powered by OpenCog and M-Labs Lucid game engine, with the capability for simple English conversation and realistic human-like emotional dynamics. Once again, as part of this effort, PLN will play a pivotal role, supplying the core planning and inference mechanisms. As these projects proceed, it is clear that new challenges will arise and that PLN will encounter challenges and require alterations and additions. As a standalone system, many challenging problems still remain, most notably forward and backward chaining inference control.

9 Memory Specific Cognitive Processes Type Probabilistic Logic Networks (PLN) [3]; Declarative concept blending [2] MOSES (a novel probabilistic Procedural evolutionary program learning algorithm) [9] Episodic internal simulation engine [4] Attentional Economic Attention Networks (ECAN) [6] Intentional probabilistic goal hierarchy refined by PLN and ECAN, structured according to Psi Probabilistic Logic Networks 9 General Cognitive Functions pattern creation pattern creation association, pattern creation attention allocation,, association, credit assignment credit assignment, pattern creation Sensory Supplied by DeSTIN integration association, attention allocation, pattern creation, credit assignment Table 1. Memory Types and Cognitive Processes in OpenCog Prime. The third column indicates the general cognitive function that each specific cognitive process carries out, according to the patternist theory of cognition. References 1. Arel, I., Rose, D., Coop, R.: Destin: A scalable deep learning architecture with application to high-dimensional robust pattern recognition. Proc. AAAI Workshop on Biologically Inspired Cognitive Architectures (2009) 2. Fauconnier, G., Turner, M.: The Way We Think: Conceptual Blending and the Mind s Hidden Complexities. Basic (2002) 3. Goertzel, B., Ikle, M., Goertzel, I., Heljakka, A.: Probabilistic Logic Networks. Springer (2008) 4. Goertzel, B., Et Al, C.P.: An integrative methodology for teaching embodied nonlinguistic agents, applied to virtual animals in second life. In: Proc.of the First Conf. on AGI. IOS Press (2008) 5. Goertzel, B., Pinto, H., Pennachin, C., Goertzel, I.F.: Using dependency parsing and probabilistic inference to extract relationships between genes, proteins and malignancies implicit among multiple biomedical research abstracts. In: Proc. of Bio-NLP 2006 (2006) 6. Goertzel, B., Pitt, J., Ikle, M., Pennachin, C., Liu, R.: Glocal memory: a design principle for artificial brains and minds. Neurocomputing (Apr 2010) 7. Hart, D., Goertzel, B.: Opencog: A software framework for integrative artificial general intelligence. In: AGI. Frontiers in Artificial Intelligence and Applications, vol. 171, pp IOS Press (2008), agi/agi2008.html#hartg08 8. Legg, S., Hutter, M.: A formal measure of machine intelligence. In: Proc. of Benelaam, 2006 (2007) 9. Looks, M.: Competent Program Evolution. PhD Thesis, Computer Science Department, Washington University (2006)

10 10 Probabilistic Logic Networks 10. Tulving, E., Craik, R.: The Oxford Handbook of Memory. Oxford U. Press (2005) 11. Walley, P.: Statistical Reasoning with Imprecise Probabilities. Chapman-Hall (1990) 12. Wang, P.: Non-Axiomatic Reasoning System: Exploring the Essence of Intelligence. Ph.D. thesis, Indiana University (1995)

Wason's Cards: What is Wrong?

Wason's Cards: What is Wrong? Wason's Cards: What is Wrong? Pei Wang Computer and Information Sciences, Temple University This paper proposes a new interpretation

More information

The Logic of Categorization

The Logic of Categorization From: FLAIRS-02 Proceedings. Copyright 2002, AAAI (www.aaai.org). All rights reserved. The Logic of Categorization Pei Wang Department of Computer and Information Sciences, Temple University Philadelphia,

More information

Chapter 2. Knowledge Representation: Reasoning, Issues, and Acquisition. Teaching Notes

Chapter 2. Knowledge Representation: Reasoning, Issues, and Acquisition. Teaching Notes Chapter 2 Knowledge Representation: Reasoning, Issues, and Acquisition Teaching Notes This chapter explains how knowledge is represented in artificial intelligence. The topic may be launched by introducing

More information

Cognitive Neuroscience History of Neural Networks in Artificial Intelligence The concept of neural network in artificial intelligence

Cognitive Neuroscience History of Neural Networks in Artificial Intelligence The concept of neural network in artificial intelligence Cognitive Neuroscience History of Neural Networks in Artificial Intelligence The concept of neural network in artificial intelligence To understand the network paradigm also requires examining the history

More information

A prediction model for type 2 diabetes using adaptive neuro-fuzzy interface system.

A prediction model for type 2 diabetes using adaptive neuro-fuzzy interface system. Biomedical Research 208; Special Issue: S69-S74 ISSN 0970-938X www.biomedres.info A prediction model for type 2 diabetes using adaptive neuro-fuzzy interface system. S Alby *, BL Shivakumar 2 Research

More information

Stepwise Knowledge Acquisition in a Fuzzy Knowledge Representation Framework

Stepwise Knowledge Acquisition in a Fuzzy Knowledge Representation Framework Stepwise Knowledge Acquisition in a Fuzzy Knowledge Representation Framework Thomas E. Rothenfluh 1, Karl Bögl 2, and Klaus-Peter Adlassnig 2 1 Department of Psychology University of Zurich, Zürichbergstraße

More information

Rethinking Cognitive Architecture!

Rethinking Cognitive Architecture! Rethinking Cognitive Architecture! Reconciling Uniformity and Diversity via Graphical Models! Paul Rosenbloom!!! 1/25/2010! Department of Computer Science &! Institute for Creative Technologies! The projects

More information

ERA: Architectures for Inference

ERA: Architectures for Inference ERA: Architectures for Inference Dan Hammerstrom Electrical And Computer Engineering 7/28/09 1 Intelligent Computing In spite of the transistor bounty of Moore s law, there is a large class of problems

More information

High-level Vision. Bernd Neumann Slides for the course in WS 2004/05. Faculty of Informatics Hamburg University Germany

High-level Vision. Bernd Neumann Slides for the course in WS 2004/05. Faculty of Informatics Hamburg University Germany High-level Vision Bernd Neumann Slides for the course in WS 2004/05 Faculty of Informatics Hamburg University Germany neumann@informatik.uni-hamburg.de http://kogs-www.informatik.uni-hamburg.de 1 Contents

More information

Grounding Ontologies in the External World

Grounding Ontologies in the External World Grounding Ontologies in the External World Antonio CHELLA University of Palermo and ICAR-CNR, Palermo antonio.chella@unipa.it Abstract. The paper discusses a case study of grounding an ontology in the

More information

Plan Recognition through Goal Graph Analysis

Plan Recognition through Goal Graph Analysis Plan Recognition through Goal Graph Analysis Jun Hong 1 Abstract. We present a novel approach to plan recognition based on a two-stage paradigm of graph construction and analysis. First, a graph structure

More information

LECTURE 5: REACTIVE AND HYBRID ARCHITECTURES

LECTURE 5: REACTIVE AND HYBRID ARCHITECTURES Reactive Architectures LECTURE 5: REACTIVE AND HYBRID ARCHITECTURES An Introduction to MultiAgent Systems http://www.csc.liv.ac.uk/~mjw/pubs/imas There are many unsolved (some would say insoluble) problems

More information

Learning to Use Episodic Memory

Learning to Use Episodic Memory Learning to Use Episodic Memory Nicholas A. Gorski (ngorski@umich.edu) John E. Laird (laird@umich.edu) Computer Science & Engineering, University of Michigan 2260 Hayward St., Ann Arbor, MI 48109 USA Abstract

More information

Computational Cognitive Neuroscience

Computational Cognitive Neuroscience Computational Cognitive Neuroscience Computational Cognitive Neuroscience Computational Cognitive Neuroscience *Computer vision, *Pattern recognition, *Classification, *Picking the relevant information

More information

CS343: Artificial Intelligence

CS343: Artificial Intelligence CS343: Artificial Intelligence Introduction: Part 2 Prof. Scott Niekum University of Texas at Austin [Based on slides created by Dan Klein and Pieter Abbeel for CS188 Intro to AI at UC Berkeley. All materials

More information

Evolutionary Approach to Investigations of Cognitive Systems

Evolutionary Approach to Investigations of Cognitive Systems Evolutionary Approach to Investigations of Cognitive Systems Vladimir RED KO a,1 b and Anton KOVAL a Scientific Research Institute for System Analysis, Russian Academy of Science, Russia b National Nuclear

More information

Evolutionary Programming

Evolutionary Programming Evolutionary Programming Searching Problem Spaces William Power April 24, 2016 1 Evolutionary Programming Can we solve problems by mi:micing the evolutionary process? Evolutionary programming is a methodology

More information

Models for Inexact Reasoning. Imprecision and Approximate Reasoning. Miguel García Remesal Department of Artificial Intelligence

Models for Inexact Reasoning. Imprecision and Approximate Reasoning. Miguel García Remesal Department of Artificial Intelligence Models for Inexact Reasoning Introduction to Uncertainty, Imprecision and Approximate Reasoning Miguel García Remesal Department of Artificial Intelligence mgremesal@fi.upm.es Uncertainty and Imprecision

More information

M.Sc. in Cognitive Systems. Model Curriculum

M.Sc. in Cognitive Systems. Model Curriculum M.Sc. in Cognitive Systems Model Curriculum April 2014 Version 1.0 School of Informatics University of Skövde Sweden Contents 1 CORE COURSES...1 2 ELECTIVE COURSES...1 3 OUTLINE COURSE SYLLABI...2 Page

More information

The Development and Application of Bayesian Networks Used in Data Mining Under Big Data

The Development and Application of Bayesian Networks Used in Data Mining Under Big Data 2017 International Conference on Arts and Design, Education and Social Sciences (ADESS 2017) ISBN: 978-1-60595-511-7 The Development and Application of Bayesian Networks Used in Data Mining Under Big Data

More information

EEL-5840 Elements of {Artificial} Machine Intelligence

EEL-5840 Elements of {Artificial} Machine Intelligence Menu Introduction Syllabus Grading: Last 2 Yrs Class Average 3.55; {3.7 Fall 2012 w/24 students & 3.45 Fall 2013} General Comments Copyright Dr. A. Antonio Arroyo Page 2 vs. Artificial Intelligence? DEF:

More information

Artificial Intelligence Lecture 7

Artificial Intelligence Lecture 7 Artificial Intelligence Lecture 7 Lecture plan AI in general (ch. 1) Search based AI (ch. 4) search, games, planning, optimization Agents (ch. 8) applied AI techniques in robots, software agents,... Knowledge

More information

Coherence Theory of Truth as Base for Knowledge Based Systems

Coherence Theory of Truth as Base for Knowledge Based Systems Association for Information Systems AIS Electronic Library (AISeL) AMCIS 1996 Proceedings Americas Conference on Information Systems (AMCIS) 8-16-1996 Coherence Theory of Truth as Base for Knowledge Based

More information

Causal Knowledge Modeling for Traditional Chinese Medicine using OWL 2

Causal Knowledge Modeling for Traditional Chinese Medicine using OWL 2 Causal Knowledge Modeling for Traditional Chinese Medicine using OWL 2 Peiqin Gu College of Computer Science, Zhejiang University, P.R.China gupeiqin@zju.edu.cn Abstract. Unlike Western Medicine, those

More information

INTERVIEWS II: THEORIES AND TECHNIQUES 5. CLINICAL APPROACH TO INTERVIEWING PART 1

INTERVIEWS II: THEORIES AND TECHNIQUES 5. CLINICAL APPROACH TO INTERVIEWING PART 1 INTERVIEWS II: THEORIES AND TECHNIQUES 5. CLINICAL APPROACH TO INTERVIEWING PART 1 5.1 Clinical Interviews: Background Information The clinical interview is a technique pioneered by Jean Piaget, in 1975,

More information

arxiv: v1 [cs.ai] 13 Mar 2017

arxiv: v1 [cs.ai] 13 Mar 2017 Toward a Formal Model of Cognitive Synergy Ben Goertzel OpenCog Foundation, Hong Kong ben@goertzel.org October 10, 2018 arxiv:1703.04361v1 [cs.ai] 13 Mar 2017 Abstract Cognitive synergy refers to a dynamic

More information

Cognitive and Biological Agent Models for Emotion Reading

Cognitive and Biological Agent Models for Emotion Reading Cognitive and Biological Agent Models for Emotion Reading Zulfiqar A. Memon, Jan Treur Vrije Universiteit Amsterdam, Department of Artificial Intelligence De Boelelaan 1081, 1081 HV Amsterdam, the Netherlands

More information

Critical Thinking Assessment at MCC. How are we doing?

Critical Thinking Assessment at MCC. How are we doing? Critical Thinking Assessment at MCC How are we doing? Prepared by Maura McCool, M.S. Office of Research, Evaluation and Assessment Metropolitan Community Colleges Fall 2003 1 General Education Assessment

More information

A Brief Introduction to Bayesian Statistics

A Brief Introduction to Bayesian Statistics A Brief Introduction to Statistics David Kaplan Department of Educational Psychology Methods for Social Policy Research and, Washington, DC 2017 1 / 37 The Reverend Thomas Bayes, 1701 1761 2 / 37 Pierre-Simon

More information

Implementation of Inference Engine in Adaptive Neuro Fuzzy Inference System to Predict and Control the Sugar Level in Diabetic Patient

Implementation of Inference Engine in Adaptive Neuro Fuzzy Inference System to Predict and Control the Sugar Level in Diabetic Patient , ISSN (Print) : 319-8613 Implementation of Inference Engine in Adaptive Neuro Fuzzy Inference System to Predict and Control the Sugar Level in Diabetic Patient M. Mayilvaganan # 1 R. Deepa * # Associate

More information

An Escalation Model of Consciousness

An Escalation Model of Consciousness Bailey!1 Ben Bailey Current Issues in Cognitive Science Mark Feinstein 2015-12-18 An Escalation Model of Consciousness Introduction The idea of consciousness has plagued humanity since its inception. Humans

More information

Handling Partial Preferences in the Belief AHP Method: Application to Life Cycle Assessment

Handling Partial Preferences in the Belief AHP Method: Application to Life Cycle Assessment Handling Partial Preferences in the Belief AHP Method: Application to Life Cycle Assessment Amel Ennaceur 1, Zied Elouedi 1, and Eric Lefevre 2 1 University of Tunis, Institut Supérieur de Gestion de Tunis,

More information

Artificial Cognitive Systems

Artificial Cognitive Systems Artificial Cognitive Systems David Vernon Carnegie Mellon University Africa vernon@cmu.edu www.vernon.eu Artificial Cognitive Systems 1 Carnegie Mellon University Africa Lecture 2 Paradigms of Cognitive

More information

Intelligent Machines That Act Rationally. Hang Li Toutiao AI Lab

Intelligent Machines That Act Rationally. Hang Li Toutiao AI Lab Intelligent Machines That Act Rationally Hang Li Toutiao AI Lab Four Definitions of Artificial Intelligence Building intelligent machines (i.e., intelligent computers) Thinking humanly Acting humanly Thinking

More information

Cognitive Maps-Based Student Model

Cognitive Maps-Based Student Model Cognitive Maps-Based Student Model Alejandro Peña 1,2,3, Humberto Sossa 3, Agustín Gutiérrez 3 WOLNM 1, UPIICSA 2 & CIC 3 - National Polytechnic Institute 2,3, Mexico 31 Julio 1859, # 1099-B, Leyes Reforma,

More information

Computational Neuroscience. Instructor: Odelia Schwartz

Computational Neuroscience. Instructor: Odelia Schwartz Computational Neuroscience 2017 1 Instructor: Odelia Schwartz From the NIH web site: Committee report: Brain 2025: A Scientific Vision (from 2014) #1. Discovering diversity: Identify and provide experimental

More information

Organizational. Architectures of Cognition Lecture 1. What cognitive phenomena will we examine? Goals of this course. Practical Assignments.

Organizational. Architectures of Cognition Lecture 1. What cognitive phenomena will we examine? Goals of this course. Practical Assignments. Architectures of Cognition Lecture 1 Niels Taatgen Artificial Intelligence Webpage: http://www.ai.rug.nl/avi 2 Organizational Practical assignments start Next Week Work in pairs 3 assignments Grade = (1/4)*assignments

More information

Intelligent Machines That Act Rationally. Hang Li Bytedance AI Lab

Intelligent Machines That Act Rationally. Hang Li Bytedance AI Lab Intelligent Machines That Act Rationally Hang Li Bytedance AI Lab Four Definitions of Artificial Intelligence Building intelligent machines (i.e., intelligent computers) Thinking humanly Acting humanly

More information

CS148 - Building Intelligent Robots Lecture 5: Autonomus Control Architectures. Instructor: Chad Jenkins (cjenkins)

CS148 - Building Intelligent Robots Lecture 5: Autonomus Control Architectures. Instructor: Chad Jenkins (cjenkins) Lecture 5 Control Architectures Slide 1 CS148 - Building Intelligent Robots Lecture 5: Autonomus Control Architectures Instructor: Chad Jenkins (cjenkins) Lecture 5 Control Architectures Slide 2 Administrivia

More information

Functionalism. (1) Machine Functionalism

Functionalism. (1) Machine Functionalism Functionalism As Levine indicates, from a functionalist viewpoint, the status of a mental state is not given by its internal constitution but by its function. For instance, a thought or a pain depends

More information

Agent-Based Systems. Agent-Based Systems. Michael Rovatsos. Lecture 5 Reactive and Hybrid Agent Architectures 1 / 19

Agent-Based Systems. Agent-Based Systems. Michael Rovatsos. Lecture 5 Reactive and Hybrid Agent Architectures 1 / 19 Agent-Based Systems Michael Rovatsos mrovatso@inf.ed.ac.uk Lecture 5 Reactive and Hybrid Agent Architectures 1 / 19 Where are we? Last time... Practical reasoning agents The BDI architecture Intentions

More information

FUZZY LOGIC AND FUZZY SYSTEMS: RECENT DEVELOPMENTS AND FUTURE DIWCTIONS

FUZZY LOGIC AND FUZZY SYSTEMS: RECENT DEVELOPMENTS AND FUTURE DIWCTIONS FUZZY LOGIC AND FUZZY SYSTEMS: RECENT DEVELOPMENTS AND FUTURE DIWCTIONS Madan M. Gupta Intelligent Systems Research Laboratory College of Engineering University of Saskatchewan Saskatoon, Sask. Canada,

More information

Local Image Structures and Optic Flow Estimation

Local Image Structures and Optic Flow Estimation Local Image Structures and Optic Flow Estimation Sinan KALKAN 1, Dirk Calow 2, Florentin Wörgötter 1, Markus Lappe 2 and Norbert Krüger 3 1 Computational Neuroscience, Uni. of Stirling, Scotland; {sinan,worgott}@cn.stir.ac.uk

More information

How Does Analysis of Competing Hypotheses (ACH) Improve Intelligence Analysis?

How Does Analysis of Competing Hypotheses (ACH) Improve Intelligence Analysis? How Does Analysis of Competing Hypotheses (ACH) Improve Intelligence Analysis? Richards J. Heuer, Jr. Version 1.2, October 16, 2005 This document is from a collection of works by Richards J. Heuer, Jr.

More information

Artificial Intelligence Programming Probability

Artificial Intelligence Programming Probability Artificial Intelligence Programming Probability Chris Brooks Department of Computer Science University of San Francisco Department of Computer Science University of San Francisco p.1/25 17-0: Uncertainty

More information

Representation Theorems for Multiple Belief Changes

Representation Theorems for Multiple Belief Changes Representation Theorems for Multiple Belief Changes Dongmo Zhang 1,2 Shifu Chen 1 Wujia Zhu 1,2 Zhaoqian Chen 1 1 State Key Lab. for Novel Software Technology Department of Computer Science and Technology

More information

2012 Course: The Statistician Brain: the Bayesian Revolution in Cognitive Sciences

2012 Course: The Statistician Brain: the Bayesian Revolution in Cognitive Sciences 2012 Course: The Statistician Brain: the Bayesian Revolution in Cognitive Sciences Stanislas Dehaene Chair of Experimental Cognitive Psychology Lecture n 5 Bayesian Decision-Making Lecture material translated

More information

Some Connectivity Concepts in Bipolar Fuzzy Graphs

Some Connectivity Concepts in Bipolar Fuzzy Graphs Annals of Pure and Applied Mathematics Vol. 7, No. 2, 2014, 98-108 ISSN: 2279-087X (P), 2279-0888(online) Published on 30 September 2014 www.researchmathsci.org Annals of Some Connectivity Concepts in

More information

An Introduction to CLARION. Ryan Allison. Rensselaer Polytechnic Institute

An Introduction to CLARION. Ryan Allison. Rensselaer Polytechnic Institute Intro to CLARION 1 An Introduction to CLARION Ryan Allison Rensselaer Polytechnic Institute Intro to CLARION 2 An Introduction to CLARION Psychologists have been puzzling over the workings of the mind

More information

Semiotics and Intelligent Control

Semiotics and Intelligent Control Semiotics and Intelligent Control Morten Lind 0rsted-DTU: Section of Automation, Technical University of Denmark, DK-2800 Kgs. Lyngby, Denmark. m/i@oersted.dtu.dk Abstract: Key words: The overall purpose

More information

Lecture 2: Foundations of Concept Learning

Lecture 2: Foundations of Concept Learning Lecture 2: Foundations of Concept Learning Cognitive Systems - Machine Learning Part I: Basic Approaches to Concept Learning Version Space, Candidate Elimination, Inductive Bias last change October 18,

More information

Plan Recognition through Goal Graph Analysis

Plan Recognition through Goal Graph Analysis Plan Recognition through Goal Graph Analysis Jun Hong 1 Abstract. We present a novel approach to plan recognition based on a two-stage paradigm of graph construction and analysis. First, a graph structure

More information

Minimal Change and Maximal Coherence: A Basis for Belief Revision and Reasoning about Actions

Minimal Change and Maximal Coherence: A Basis for Belief Revision and Reasoning about Actions Minimal Change and Maximal Coherence: A Basis for Belief Revision and Reasoning about Actions Anand S. Rao Australian AI Institute Carlton, Vic-3053 Australia Email: anand@aaii.oz.au Abstract The study

More information

Spatial Cognition for Mobile Robots: A Hierarchical Probabilistic Concept- Oriented Representation of Space

Spatial Cognition for Mobile Robots: A Hierarchical Probabilistic Concept- Oriented Representation of Space Spatial Cognition for Mobile Robots: A Hierarchical Probabilistic Concept- Oriented Representation of Space Shrihari Vasudevan Advisor: Prof. Dr. Roland Siegwart Autonomous Systems Lab, ETH Zurich, Switzerland.

More information

Robotics Summary. Made by: Iskaj Janssen

Robotics Summary. Made by: Iskaj Janssen Robotics Summary Made by: Iskaj Janssen Multiagent system: System composed of multiple agents. Five global computing trends: 1. Ubiquity (computers and intelligence are everywhere) 2. Interconnection (networked

More information

A Comparison of Collaborative Filtering Methods for Medication Reconciliation

A Comparison of Collaborative Filtering Methods for Medication Reconciliation A Comparison of Collaborative Filtering Methods for Medication Reconciliation Huanian Zheng, Rema Padman, Daniel B. Neill The H. John Heinz III College, Carnegie Mellon University, Pittsburgh, PA, 15213,

More information

WP 7: Emotion in Cognition and Action

WP 7: Emotion in Cognition and Action WP 7: Emotion in Cognition and Action Lola Cañamero, UH 2 nd Plenary, May 24-27 2005, Newcastle WP7: The context Emotion in cognition & action in multi-modal interfaces? Emotion-oriented systems adapted

More information

1 What is an Agent? CHAPTER 2: INTELLIGENT AGENTS

1 What is an Agent? CHAPTER 2: INTELLIGENT AGENTS 1 What is an Agent? CHAPTER 2: INTELLIGENT AGENTS http://www.csc.liv.ac.uk/ mjw/pubs/imas/ The main point about agents is they are autonomous: capable of acting independently, exhibiting control over their

More information

Chapter 1. Introduction

Chapter 1. Introduction Chapter 1 Introduction 1.1 Motivation and Goals The increasing availability and decreasing cost of high-throughput (HT) technologies coupled with the availability of computational tools and data form a

More information

Behavior Architectures

Behavior Architectures Behavior Architectures 5 min reflection You ve read about two very different behavior architectures. What are the most significant functional/design differences between the two approaches? Are they compatible

More information

From Maths/Music Theory to Memory Evolutive Systems

From Maths/Music Theory to Memory Evolutive Systems From Maths/Music Theory to Memory Evolutive Systems Abstract. This article presents a first attempt at establishing a category-theoretical model of creative processes. The model, which is applied to musical

More information

PIB Ch. 18 Sequence Memory for Prediction, Inference, and Behavior. Jeff Hawkins, Dileep George, and Jamie Niemasik Presented by Jiseob Kim

PIB Ch. 18 Sequence Memory for Prediction, Inference, and Behavior. Jeff Hawkins, Dileep George, and Jamie Niemasik Presented by Jiseob Kim PIB Ch. 18 Sequence Memory for Prediction, Inference, and Behavior Jeff Hawkins, Dileep George, and Jamie Niemasik Presented by Jiseob Kim Quiz Briefly describe the neural activities of minicolumn in the

More information

Artificial Intelligence For Homeopathic Remedy Selection

Artificial Intelligence For Homeopathic Remedy Selection Artificial Intelligence For Homeopathic Remedy Selection A. R. Pawar, amrut.pawar@yahoo.co.in, S. N. Kini, snkini@gmail.com, M. R. More mangeshmore88@gmail.com Department of Computer Science and Engineering,

More information

Human Activities: Handling Uncertainties Using Fuzzy Time Intervals

Human Activities: Handling Uncertainties Using Fuzzy Time Intervals The 19th International Conference on Pattern Recognition (ICPR), Tampa, FL, 2009 Human Activities: Handling Uncertainties Using Fuzzy Time Intervals M. S. Ryoo 1,2 and J. K. Aggarwal 1 1 Computer & Vision

More information

A FRAMEWORK FOR CLINICAL DECISION SUPPORT IN INTERNAL MEDICINE A PRELIMINARY VIEW Kopecky D 1, Adlassnig K-P 1

A FRAMEWORK FOR CLINICAL DECISION SUPPORT IN INTERNAL MEDICINE A PRELIMINARY VIEW Kopecky D 1, Adlassnig K-P 1 A FRAMEWORK FOR CLINICAL DECISION SUPPORT IN INTERNAL MEDICINE A PRELIMINARY VIEW Kopecky D 1, Adlassnig K-P 1 Abstract MedFrame provides a medical institution with a set of software tools for developing

More information

Fuzzy Expert System Design for Medical Diagnosis

Fuzzy Expert System Design for Medical Diagnosis Second International Conference Modelling and Development of Intelligent Systems Sibiu - Romania, September 29 - October 02, 2011 Man Diana Ofelia Abstract In recent years, the methods of artificial intelligence

More information

The Unicist Paradigm Shift in Sciences

The Unicist Paradigm Shift in Sciences 1 The Unicist Theory explains the dynamics and evolution of living beings and complex adaptive entities. The Unicist Paradigm Shift in Sciences An Introduction to the Unicist Theory, its Scientific Evidences

More information

Design Methodology. 4th year 1 nd Semester. M.S.C. Madyan Rashan. Room No Academic Year

Design Methodology. 4th year 1 nd Semester. M.S.C. Madyan Rashan. Room No Academic Year College of Engineering Department of Interior Design Design Methodology 4th year 1 nd Semester M.S.C. Madyan Rashan Room No. 313 Academic Year 2018-2019 Course Name Course Code INDS 315 Lecturer in Charge

More information

1. INTRODUCTION. Vision based Multi-feature HGR Algorithms for HCI using ISL Page 1

1. INTRODUCTION. Vision based Multi-feature HGR Algorithms for HCI using ISL Page 1 1. INTRODUCTION Sign language interpretation is one of the HCI applications where hand gesture plays important role for communication. This chapter discusses sign language interpretation system with present

More information

Between-word regressions as part of rational reading

Between-word regressions as part of rational reading Between-word regressions as part of rational reading Klinton Bicknell & Roger Levy UC San Diego CUNY 2010: New York Bicknell & Levy (UC San Diego) Regressions as rational reading CUNY 2010 1 / 23 Introduction

More information

Hierarchical Bayesian Modeling of Individual Differences in Texture Discrimination

Hierarchical Bayesian Modeling of Individual Differences in Texture Discrimination Hierarchical Bayesian Modeling of Individual Differences in Texture Discrimination Timothy N. Rubin (trubin@uci.edu) Michael D. Lee (mdlee@uci.edu) Charles F. Chubb (cchubb@uci.edu) Department of Cognitive

More information

Sparse Coding in Sparse Winner Networks

Sparse Coding in Sparse Winner Networks Sparse Coding in Sparse Winner Networks Janusz A. Starzyk 1, Yinyin Liu 1, David Vogel 2 1 School of Electrical Engineering & Computer Science Ohio University, Athens, OH 45701 {starzyk, yliu}@bobcat.ent.ohiou.edu

More information

Implementation of Perception Classification based on BDI Model using Bayesian Classifier

Implementation of Perception Classification based on BDI Model using Bayesian Classifier Implementation of Perception Classification based on BDI Model using Bayesian Classifier Vishwanath Y 1 Murali T S 2 Dr M.V Vijayakumar 3 1 Research Scholar, Dept. of Computer Science & Engineering, Jain

More information

Learning Deterministic Causal Networks from Observational Data

Learning Deterministic Causal Networks from Observational Data Carnegie Mellon University Research Showcase @ CMU Department of Psychology Dietrich College of Humanities and Social Sciences 8-22 Learning Deterministic Causal Networks from Observational Data Ben Deverett

More information

Bayesian Belief Network Based Fault Diagnosis in Automotive Electronic Systems

Bayesian Belief Network Based Fault Diagnosis in Automotive Electronic Systems Bayesian Belief Network Based Fault Diagnosis in Automotive Electronic Systems Yingping Huang *, David Antory, R. Peter Jones, Craig Groom, Ross McMurran, Peter Earp and Francis Mckinney International

More information

Introduction to Bayesian Analysis 1

Introduction to Bayesian Analysis 1 Biostats VHM 801/802 Courses Fall 2005, Atlantic Veterinary College, PEI Henrik Stryhn Introduction to Bayesian Analysis 1 Little known outside the statistical science, there exist two different approaches

More information

Marcus Hutter Canberra, ACT, 0200, Australia

Marcus Hutter Canberra, ACT, 0200, Australia Marcus Hutter Canberra, ACT, 0200, Australia http://www.hutter1.net/ Australian National University Abstract The approaches to Artificial Intelligence (AI) in the last century may be labelled as (a) trying

More information

Novamente: An Integrative Architecture for General Intelligence

Novamente: An Integrative Architecture for General Intelligence Novamente: An Integrative Architecture for General Intelligence Moshe Looks 1, Ben Goertzel 2 and Cassio Pennachin 2 1. Object Sciences Corporation 6359 Walker Lane Suite 100 Alexandria, VA 22310 mlooks@objectsciences.com

More information

Inferencing in Artificial Intelligence and Computational Linguistics

Inferencing in Artificial Intelligence and Computational Linguistics Inferencing in Artificial Intelligence and Computational Linguistics (http://www.dfki.de/~horacek/infer-ai-cl.html) no classes on 28.5., 18.6., 25.6. 2-3 extra lectures will be scheduled Helmut Horacek

More information

The Ordinal Nature of Emotions. Georgios N. Yannakakis, Roddy Cowie and Carlos Busso

The Ordinal Nature of Emotions. Georgios N. Yannakakis, Roddy Cowie and Carlos Busso The Ordinal Nature of Emotions Georgios N. Yannakakis, Roddy Cowie and Carlos Busso The story It seems that a rank-based FeelTrace yields higher inter-rater agreement Indeed, FeelTrace should actually

More information

Computational Explorations in Cognitive Neuroscience Chapter 7: Large-Scale Brain Area Functional Organization

Computational Explorations in Cognitive Neuroscience Chapter 7: Large-Scale Brain Area Functional Organization Computational Explorations in Cognitive Neuroscience Chapter 7: Large-Scale Brain Area Functional Organization 1 7.1 Overview This chapter aims to provide a framework for modeling cognitive phenomena based

More information

Artificial intelligence (and Searle s objection) COS 116: 4/29/2008 Sanjeev Arora

Artificial intelligence (and Searle s objection) COS 116: 4/29/2008 Sanjeev Arora Artificial intelligence (and Searle s objection) COS 116: 4/29/2008 Sanjeev Arora Artificial Intelligence Definition of AI (Merriam-Webster): The capability of a machine to imitate intelligent human behavior

More information

Artificial Intelligence and Human Thinking. Robert Kowalski Imperial College London

Artificial Intelligence and Human Thinking. Robert Kowalski Imperial College London Artificial Intelligence and Human Thinking Robert Kowalski Imperial College London 1 Artificial Intelligence and Human Thinking The Abductive Logic Programming (ALP) agent model as a unifying framework

More information

P(HYP)=h. P(CON HYP)=p REL. P(CON HYP)=q REP

P(HYP)=h. P(CON HYP)=p REL. P(CON HYP)=q REP BAYESIAN NETWORKS IN PHILOSOPHY STEPHAN HARTMANN, LUC BOVENS 1. Introduction There is a long philosophical tradition of addressing questions in philosophy of science and epistemology by means of the tools

More information

Outline. What s inside this paper? My expectation. Software Defect Prediction. Traditional Method. What s inside this paper?

Outline. What s inside this paper? My expectation. Software Defect Prediction. Traditional Method. What s inside this paper? Outline A Critique of Software Defect Prediction Models Norman E. Fenton Dongfeng Zhu What s inside this paper? What kind of new technique was developed in this paper? Research area of this technique?

More information

International Journal of Software and Web Sciences (IJSWS)

International Journal of Software and Web Sciences (IJSWS) International Association of Scientific Innovation and Research (IASIR) (An Association Unifying the Sciences, Engineering, and Applied Research) ISSN (Print): 2279-0063 ISSN (Online): 2279-0071 International

More information

arxiv: v1 [cs.ai] 5 Oct 2018 October 8, 2018

arxiv: v1 [cs.ai] 5 Oct 2018 October 8, 2018 André Ofner Research Focus Cognitive Sciences University of Potsdam Potsdam, Germany ofner@uni-potsdam.de Sebastian Stober Artificial Intelligence Lab Otto von Guericke University Magdeburg, Germany stober@ovgu.de

More information

L6: Overview. with side orders of lecture revision, pokemon, and silly experiments. Dani Navarro

L6: Overview. with side orders of lecture revision, pokemon, and silly experiments. Dani Navarro L6: Overview with side orders of lecture revision, pokemon, and silly experiments Dani Navarro Part 1: Dani Navarro L1: Introduction L2: Attention L3: Similarity L4: Reasoning L5: A case study Part 2:

More information

Models of Information Retrieval

Models of Information Retrieval Models of Information Retrieval Introduction By information behaviour is meant those activities a person may engage in when identifying their own needs for information, searching for such information in

More information

Dynamic Rule-based Agent

Dynamic Rule-based Agent International Journal of Engineering Research and Technology. ISSN 0974-3154 Volume 11, Number 4 (2018), pp. 605-613 International Research Publication House http://www.irphouse.com Dynamic Rule-based

More information

Goal-Oriented Measurement plus System Dynamics A Hybrid and Evolutionary Approach

Goal-Oriented Measurement plus System Dynamics A Hybrid and Evolutionary Approach Goal-Oriented Measurement plus System Dynamics A Hybrid and Evolutionary Approach Dietmar Pfahl Fraunhofer Institute IESE pfahl@iese.fhg.de Günther Ruhe University of Calgary ruhe@ucalgary.ca 1. Aim and

More information

Introduction to Computational Neuroscience

Introduction to Computational Neuroscience Introduction to Computational Neuroscience Lecture 5: Data analysis II Lesson Title 1 Introduction 2 Structure and Function of the NS 3 Windows to the Brain 4 Data analysis 5 Data analysis II 6 Single

More information

ICS 606. Intelligent Autonomous Agents 1. Intelligent Autonomous Agents ICS 606 / EE 606 Fall Reactive Architectures

ICS 606. Intelligent Autonomous Agents 1. Intelligent Autonomous Agents ICS 606 / EE 606 Fall Reactive Architectures Intelligent Autonomous Agents ICS 606 / EE 606 Fall 2011 Nancy E. Reed nreed@hawaii.edu 1 Lecture #5 Reactive and Hybrid Agents Reactive Architectures Brooks and behaviors The subsumption architecture

More information

Utility Maximization and Bounds on Human Information Processing

Utility Maximization and Bounds on Human Information Processing Topics in Cognitive Science (2014) 1 6 Copyright 2014 Cognitive Science Society, Inc. All rights reserved. ISSN:1756-8757 print / 1756-8765 online DOI: 10.1111/tops.12089 Utility Maximization and Bounds

More information

Module 1. Introduction. Version 1 CSE IIT, Kharagpur

Module 1. Introduction. Version 1 CSE IIT, Kharagpur Module 1 Introduction Lesson 2 Introduction to Agent 1.3.1 Introduction to Agents An agent acts in an environment. Percepts Agent Environment Actions An agent perceives its environment through sensors.

More information

CPS331 Lecture: Coping with Uncertainty; Discussion of Dreyfus Reading

CPS331 Lecture: Coping with Uncertainty; Discussion of Dreyfus Reading CPS331 Lecture: Coping with Uncertainty; Discussion of Dreyfus Reading Objectives: 1. To discuss ways of handling uncertainty (probability; Mycin CF) 2. To discuss Dreyfus views on expert systems Materials:

More information

Support system for breast cancer treatment

Support system for breast cancer treatment Support system for breast cancer treatment SNEZANA ADZEMOVIC Civil Hospital of Cacak, Cara Lazara bb, 32000 Cacak, SERBIA Abstract:-The aim of this paper is to seek out optimal relation between diagnostic

More information

A Computational Theory of Belief Introspection

A Computational Theory of Belief Introspection A Computational Theory of Belief Introspection Kurt Konolige Artificial Intelligence Center SRI International Menlo Park, California 94025 Abstract Introspection is a general term covering the ability

More information

Exploring Experiential Learning: Simulations and Experiential Exercises, Volume 5, 1978 THE USE OF PROGRAM BAYAUD IN THE TEACHING OF AUDIT SAMPLING

Exploring Experiential Learning: Simulations and Experiential Exercises, Volume 5, 1978 THE USE OF PROGRAM BAYAUD IN THE TEACHING OF AUDIT SAMPLING THE USE OF PROGRAM BAYAUD IN THE TEACHING OF AUDIT SAMPLING James W. Gentry, Kansas State University Mary H. Bonczkowski, Kansas State University Charles W. Caldwell, Kansas State University INTRODUCTION

More information

Embracing Complexity in System of Systems Analysis and Architecting

Embracing Complexity in System of Systems Analysis and Architecting Embracing Complexity in System of Systems Analysis and Architecting Complex Adaptive System 2013 November 13-15, 2013, Baltimore, MA Cihan H. Dagli INCOSE and IIE Fellow Founder Director Systems Engineering

More information