Lesson 6 Learning II Anders Lyhne Christensen, D6.05, INTRODUCTION TO AUTONOMOUS MOBILE ROBOTS

Size: px
Start display at page:

Download "Lesson 6 Learning II Anders Lyhne Christensen, D6.05, INTRODUCTION TO AUTONOMOUS MOBILE ROBOTS"

Transcription

1 Lesson 6 Learning II Anders Lyhne Christensen, D6.05, anders.christensen@iscte.pt INTRODUCTION TO AUTONOMOUS MOBILE ROBOTS

2 First: Quick Background in Neural Nets Some of earliest work in neural networks (or connectionist systems) was McCulloch-Pitts model of neurons (1943) McCulloch-Pitts: Simple linear threshold unit Synaptic weights associated with each synaptic input If threshold exceeded, neuron fired, carrying output to next neuron Later, Rosenblatt (1958) introduced Perceptron: Input vector x 1 x 2 x 3... x n w 1 w 2 w 3... w n Synaptic weights Neuron Σ θ Output

3 Neural Net Quick Background (con t.) 1960s 1970s: neural net research in decline due to Minsky and Papertbook (1969) that proved limitations of single-layer perceptron networks 1980s: resurgence due to multi-layer neural networks and use of back-propagation as a means for training these systems Much work in connectionism since, with significant progress Keep in mind: neural nets are only abstract computational models of biological neurons

4 Methods for Encoding Behavior-Based Robotic Control in Neural Networks HebbianLearning PerceptronLearning Classical Conditioning

5 1. Hebbian Learning Hebb(1949) developed one of earliest training algorithms for neural networks Hebbianlearning: increases synaptic strength along neural pathways associated with a stimulus and a correct response Specifically: w ij (t+1) =w ij (t) + η*o i o j Donald Hebb where: w ij (t) and w ij (t+1) are synaptic weights connecting neurons i and j before and after updating η is the learning rate coefficient o i ando j are the outputs of neurons iandj, respectively

6 Perceptron Learning has been used for Robotic Learning Overall training procedure: Repeat: 1. Present an example from a set of positive and negative learning experiences. 2. Verify the output of the network as to whether it is correct or incorrect. 3. If it is incorrect, supply the correct output at the output unit. 4. Adjust the synaptic weights of the perceptrons in a manner that reduces the error between the observed output and correct output. Until satisfactory performance as manifested by convergence is achieved or some other stopping condition is met.

7 How to Update Synaptic Weights? Delta rule: used for perceptrons without hidden layers Modify synaptic weights according to the formula: (w ij ) = η*w ij *(t j -o j ) where (w ij ) is the synaptic adjustment applied to the connection between neurons i and j η is the learning rate coefficient t j ando j are the correct and incorrect outputs, respectively TheDelta rule strives to minimize the error term using a gradient descent approach

8 2. Gradient Descent Approach Gradient Descent: Refers to learning methods that seek to minimize an objective function by which system performance is measured At each point in time, the policy is to choose the next step that yields the minimal objective function value. The learning rate parameters refer to the step size taken at each point in time Each step is computed only on the basis of local information, which is extremely efficient, but introduces possibility of traps in local minima Gradient Descent Hill-Climbing: Analogous process whereby objective function is maximized Hill climbing

9 Another Method for Updating Weights: Back-Propagation Back-propagation: most commonly used method for updating synaptic weights Employs generalized version of Delta rule for use in multilayer perceptron networks (which is commonly used in robotic control and vision) Usually, synaptic weights are initialized to random values Weights are adjusted by following update rule as training instances are provided: w ij (t+1) =w ij (t) + ηδ j o i where: δ j = o j (1-o j )(t j -o j ) for an output node, and δ j = o j (1-o j )Σ k δ k w jk for a hidden layer node t j ando j are the correct and incorrect outputs, respectively The errors are propagated backward from the output layer.

10 3. Classical Conditioning Studied by Pavlov (1927), assumes that unconditioned stimuli (US) automatically generates an unconditioned response (UR) Pavlov determined: US-UR pair is defined genetically and is appropriate to ensure survival in the agent s environment In Pavlov s studies: Sight of food (US) results in dog s salivation (UR) Associations can be developed between a conditioned stimulus (CS), which has no intrinsic survival value, and the UR Further studies: Bell rings repeatedly with sight of food Leads to bell ringing alone generating salivation Ivan Pavlov NOTE: Hebbian learning can also produce classical conditioning

11 Classical Conditioning for Self-Organization of Behavior-Based Robotic System Instead of hard-wiring relationships between stimuli and responses, learning architecture permits associations to develop over time SENSORS Aversive Unconditioned Stimulus Collision Detectors Range Finder Target Detector Conditioned Stimulus Inhibition Unconditioned Response Robot Motors Appetitive Unconditioned Stimulus

12 Genetic Algorithms (GA) GAs form a class of gradient descent methods in which a high-quality solution is found by applying a set of biologically inspired operators to individual points within a search space, yielding better generations of solutions over an evolutionary time scale Fitness of each member of the population (the set of points in the search space) is computed using an evaluation function, called fitness function, that measures how well each individual performs with respect to the task Population s best members are rewarded according to their fitness Poorly performing individuals are punished or deleted from the population Over generations, the population improves the quality of its set of solutions GAs are not guaranteed to yield an optimal global solution, they generally produce high-quality solutions within reasonable amounts of time for certain problem spaces (including learning of control strategies for behavior-based robots)

13 GAs (con t.) Genetic algorithms: usually require specialized knowledge representations (encodings) to facilitate their operator s operation Encodings: take form of position-dependent bit strings in which each bit represents a gene in the string chromosome Initial population established by some means, typically randomly Genetic operators applied to big string encoding of population members Three most frequently used operators: Reproduction Crossover Mutation

14 Genetic Operators Reproduction Crossover Mutuate

15 GAs for Robot Learning Prior to operator s application, each individual s fitness is computed using fitness function For robot learning, this may involve running a robot through a series of experiments, using the encoding of the behavioral controller represented by the particular individual bit string encoding being evaluated Fitness function returns a value capturing the robot s overall performance for the set of conditions being tested

16 GAs for Robot Learning (con t.) Reproduction operator: Fittest individuals are copied exactly and replace less-fit individuals This can bedone probabilistically, usually using roulette-wheel selection Net effect: increase in ratio of highly-fit individuals relative to # of poor performers Crossover operator: Exchange of information through transfer of info between two individuals Process creates new individuals that may or may not perform better than parents Which individuals to cross over and which bit string pairs to exchange is often done randomly Net effect: increase in overall population

17 GAs for Robot Learning (con t.) Mutation operator: Simple probabilistic flipping of bit values in encoding Affects individual only Probability of mutation is generally low Net effect: ability to escape local minima Overall effect: changing population over time Final quality and length of time to obtain solution depend on nature of problem and parameters used

18 Example of GAs for Learning Behavioral Control GAs, although powerful, require some restrictions on implementation compared to previous learning approaches we ve discussed Much of learning must be done off-line, since: Significant population of robots needed for fitness testing Robots must be tested over many, many generations Simulations, fortunately, can be run much faster than real-world testing If simulation has reasonable fidelity to real robot and environment, control parameters from fittest simulated individual can be transferred to actual robot for use

19 Example Robot GA Code begin Obstacles.Create; Population.Build; for 1 to NUMBER_GENERATIONS do begin for 1 to RUNS_PER_GENERATION do begin foreach ROBOT in Population do for 1 to MAX_NUMBER_STEPS do begin ROBOT.Move end Obstacles.Recreate; end end Robots.Reproduce; Robots.Crossover; Robots.Mutate; end end

20 Hybrid Genetic/Neural Learning and Control Several researchers have combined neural nets and GAs for robot learning Typically, approach is to use GAs to learn synaptic weights for a neural controller Example by Floreano et al.: Implementation of Braitenberg-style neural controller Use of robot (Khepera) with 3 ambient light sensors and 8 IR proximity sensors Fitness functions defined for behaviors, including: Navigation and obstacle avoidance: Fitness maximizes motion and distance from obstacles Homing: Fitness ensures that power is kept at adequate levels by adding a lightseeking behavior to guide it to its black recharging area when power becomes low Grasping of balls using an added gripper: Fitness maximizes the number of objects gripped in an obstacle-free environment Most successful individual: learned to back up until it encountered something, then turned around an attempted to grip it

21 Today s task Work on projects

Learning and Adaptive Behavior, Part II

Learning and Adaptive Behavior, Part II Learning and Adaptive Behavior, Part II April 12, 2007 The man who sets out to carry a cat by its tail learns something that will always be useful and which will never grow dim or doubtful. -- Mark Twain

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

Learning in neural networks

Learning in neural networks http://ccnl.psy.unipd.it Learning in neural networks Marco Zorzi University of Padova M. Zorzi - European Diploma in Cognitive and Brain Sciences, Cognitive modeling", HWK 19-24/3/2006 1 Connectionist

More information

An Artificial Synaptic Plasticity Mechanism for Classical Conditioning with Neural Networks

An Artificial Synaptic Plasticity Mechanism for Classical Conditioning with Neural Networks An Artificial Synaptic Plasticity Mechanism for Classical Conditioning with Neural Networks Caroline Rizzi Raymundo (B) and Colin Graeme Johnson School of Computing, University of Kent, Canterbury, Kent

More information

Animal Behavior. Relevant Biological Disciplines. Inspirations => Models

Animal Behavior. Relevant Biological Disciplines. Inspirations => Models Animal Behavior Relevant Biological Disciplines Neuroscience: the study of the nervous system s anatomy, physiology, biochemistry and molecular biology Psychology: the study of mind and behavior Ethology:

More information

Artificial Neural Networks (Ref: Negnevitsky, M. Artificial Intelligence, Chapter 6)

Artificial Neural Networks (Ref: Negnevitsky, M. Artificial Intelligence, Chapter 6) Artificial Neural Networks (Ref: Negnevitsky, M. Artificial Intelligence, Chapter 6) BPNN in Practice Week 3 Lecture Notes page 1 of 1 The Hopfield Network In this network, it was designed on analogy of

More information

Chapter 5: Learning and Behavior Learning How Learning is Studied Ivan Pavlov Edward Thorndike eliciting stimulus emitted

Chapter 5: Learning and Behavior Learning How Learning is Studied Ivan Pavlov Edward Thorndike eliciting stimulus emitted Chapter 5: Learning and Behavior A. Learning-long lasting changes in the environmental guidance of behavior as a result of experience B. Learning emphasizes the fact that individual environments also play

More information

PSY 215 Lecture 13 (3/7/11) Learning & Memory Dr. Achtman PSY 215. Lecture 13 Topic: Mechanisms of Learning and Memory Chapter 13, section 13.

PSY 215 Lecture 13 (3/7/11) Learning & Memory Dr. Achtman PSY 215. Lecture 13 Topic: Mechanisms of Learning and Memory Chapter 13, section 13. PSY 215 Lecture 13 Topic: Mechanisms of Learning and Memory Chapter 13, section 13.2 Corrections: No corrections Announcements: Question # 37 was thrown out on the last test because it was confusing the

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

Chapter 1. Introduction

Chapter 1. Introduction Chapter 1 Introduction Artificial neural networks are mathematical inventions inspired by observations made in the study of biological systems, though loosely based on the actual biology. An artificial

More information

The storage and recall of memories in the hippocampo-cortical system. Supplementary material. Edmund T Rolls

The storage and recall of memories in the hippocampo-cortical system. Supplementary material. Edmund T Rolls The storage and recall of memories in the hippocampo-cortical system Supplementary material Edmund T Rolls Oxford Centre for Computational Neuroscience, Oxford, England and University of Warwick, Department

More information

Pavlovian, Skinner and other behaviourists contribution to AI

Pavlovian, Skinner and other behaviourists contribution to AI Pavlovian, Skinner and other behaviourists contribution to AI Witold KOSIŃSKI Dominika ZACZEK-CHRZANOWSKA Polish Japanese Institute of Information Technology, Research Center Polsko Japońska Wyższa Szko

More information

Rolls,E.T. (2016) Cerebral Cortex: Principles of Operation. Oxford University Press.

Rolls,E.T. (2016) Cerebral Cortex: Principles of Operation. Oxford University Press. Digital Signal Processing and the Brain Is the brain a digital signal processor? Digital vs continuous signals Digital signals involve streams of binary encoded numbers The brain uses digital, all or none,

More information

Psychology, Ch. 6. Learning Part 1

Psychology, Ch. 6. Learning Part 1 Psychology, Ch. 6 Learning Part 1 Two Main Types of Learning Associative learning- learning that certain events occur together Cognitive learning- acquisition of mental information, by observing or listening

More information

1. Introduction 1.1. About the content

1. Introduction 1.1. About the content 1. Introduction 1.1. About the content At first, some background ideas are given and what the origins of neurocomputing and artificial neural networks were. Then we start from single neurons or computing

More information

1. Introduction 1.1. About the content. 1.2 On the origin and development of neurocomputing

1. Introduction 1.1. About the content. 1.2 On the origin and development of neurocomputing 1. Introduction 1.1. About the content At first, some background ideas are given and what the origins of neurocomputing and artificial neural networks were. Then we start from single neurons or computing

More information

Reinforcement Learning. With help from

Reinforcement Learning. With help from Reinforcement Learning With help from A Taxonomoy of Learning L. of representations, models, behaviors, facts, Unsupervised L. Self-supervised L. Reinforcement L. Imitation L. Instruction-based L. Supervised

More information

Psychological Hodgepodge. Mr. Mattingly Psychology

Psychological Hodgepodge. Mr. Mattingly Psychology Psychological Hodgepodge Mr. Mattingly Psychology The Number: Eight What is conditioning? Conditioning = learned or trained Classical Conditioning = learning procedure where associations are made Usually

More information

Learning. Learning: Problems. Chapter 6: Learning

Learning. Learning: Problems. Chapter 6: Learning Chapter 6: Learning 1 Learning 1. In perception we studied that we are responsive to stimuli in the external world. Although some of these stimulus-response associations are innate many are learnt. 2.

More information

Neuromorphic computing

Neuromorphic computing Neuromorphic computing Robotics M.Sc. programme in Computer Science lorenzo.vannucci@santannapisa.it April 19th, 2018 Outline 1. Introduction 2. Fundamentals of neuroscience 3. Simulating the brain 4.

More information

Reinforcement learning and the brain: the problems we face all day. Reinforcement Learning in the brain

Reinforcement learning and the brain: the problems we face all day. Reinforcement Learning in the brain Reinforcement learning and the brain: the problems we face all day Reinforcement Learning in the brain Reading: Y Niv, Reinforcement learning in the brain, 2009. Decision making at all levels Reinforcement

More information

Evolution of Spiking Neural Controllers for Autonomous Vision-Based Robots

Evolution of Spiking Neural Controllers for Autonomous Vision-Based Robots Evolution of Spiking Neural Controllers for Autonomous Vision-Based Robots Dario Floreano and Claudio Mattiussi Evolutionary & Adaptive Systems, Institute of Robotics Swiss Federal Institute of Technology,

More information

Learning Classifier Systems (LCS/XCSF)

Learning Classifier Systems (LCS/XCSF) Context-Dependent Predictions and Cognitive Arm Control with XCSF Learning Classifier Systems (LCS/XCSF) Laurentius Florentin Gruber Seminar aus Künstlicher Intelligenz WS 2015/16 Professor Johannes Fürnkranz

More information

Lecture 1: Neurons. Lecture 2: Coding with spikes. To gain a basic understanding of spike based neural codes

Lecture 1: Neurons. Lecture 2: Coding with spikes. To gain a basic understanding of spike based neural codes Lecture : Neurons Lecture 2: Coding with spikes Learning objectives: To gain a basic understanding of spike based neural codes McCulloch Pitts Neuron I w in Σ out Θ Examples: I = ; θ =.5; w=. - in = *.

More information

SUPPLEMENTARY INFORMATION

SUPPLEMENTARY INFORMATION doi:1.138/nature1216 Supplementary Methods M.1 Definition and properties of dimensionality Consider an experiment with a discrete set of c different experimental conditions, corresponding to all distinct

More information

Self-organized and Evolvable Cognitive Architecture for Intelligent Agents and Multi-Agent Systems

Self-organized and Evolvable Cognitive Architecture for Intelligent Agents and Multi-Agent Systems 2010 Second International Conference on Computer Engineering and Applications Self-organized and Evolvable Cognitive Architecture for Intelligent Agents and Multi-Agent Systems Oscar Javier. Romero López

More information

Intro, Graph and Search

Intro, Graph and Search GAI Questions Intro 1. How would you describe AI (generally), to not us? 2. Game AI is really about The I of I. Which is what? Supporting the P E which is all about making the game more enjoyable Doing

More information

AP PSYCH Unit 6.1 Learning & Classical Conditioning. Before ever opening this book, what did you think learning meant?

AP PSYCH Unit 6.1 Learning & Classical Conditioning. Before ever opening this book, what did you think learning meant? AP PSYCH Unit 6.1 Learning & Classical Conditioning Before ever opening this book, what did you think learning meant? Learning We are not born with a genetic plan that gets us through our entire life Much

More information

Question 1 Multiple Choice (8 marks)

Question 1 Multiple Choice (8 marks) Philadelphia University Student Name: Faculty of Engineering Student Number: Dept. of Computer Engineering First Exam, First Semester: 2015/2016 Course Title: Neural Networks and Fuzzy Logic Date: 19/11/2015

More information

acquisition associative learning behaviorism B. F. Skinner biofeedback

acquisition associative learning behaviorism B. F. Skinner biofeedback acquisition associative learning in classical conditioning the initial stage when one links a neutral stimulus and an unconditioned stimulus so that the neutral stimulus begins triggering the conditioned

More information

Hebbian Plasticity for Improving Perceptual Decisions

Hebbian Plasticity for Improving Perceptual Decisions Hebbian Plasticity for Improving Perceptual Decisions Tsung-Ren Huang Department of Psychology, National Taiwan University trhuang@ntu.edu.tw Abstract Shibata et al. reported that humans could learn to

More information

Learning. Learning is a relatively permanent change in behavior acquired through experience.

Learning. Learning is a relatively permanent change in behavior acquired through experience. Learning Learning is a relatively permanent change in behavior acquired through experience. Classical Conditioning Learning through Association Ivan Pavlov discovered the form of learning called Classical

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

EMOTION-I Model: A Biologically-Based Theoretical Framework for Deriving Emotional Context of Sensation in Autonomous Control Systems

EMOTION-I Model: A Biologically-Based Theoretical Framework for Deriving Emotional Context of Sensation in Autonomous Control Systems 28 The Open Cybernetics and Systemics Journal, 2007, 1, 28-46 EMOTION-I Model: A Biologically-Based Theoretical Framework for Deriving Emotional Context of Sensation in Autonomous Control Systems David

More information

Artificial Neural Networks

Artificial Neural Networks Artificial Neural Networks Torsten Reil torsten.reil@zoo.ox.ac.uk Outline What are Neural Networks? Biological Neural Networks ANN The basics Feed forward net Training Example Voice recognition Applications

More information

Learning Habituation Associative learning Classical conditioning Operant conditioning Observational learning. Classical Conditioning Introduction

Learning Habituation Associative learning Classical conditioning Operant conditioning Observational learning. Classical Conditioning Introduction 1 2 3 4 5 Myers Psychology for AP* Unit 6: Learning Unit Overview How Do We Learn? Classical Conditioning Operant Conditioning Learning by Observation How Do We Learn? Introduction Learning Habituation

More information

Classical & Operant Conditioning. Learning: Principles and Applications

Classical & Operant Conditioning. Learning: Principles and Applications Classical & Operant Conditioning Learning: Principles and Applications Which Pen Would You Choose? The researchers placed the participants in the room. In this room the participants first viewed purple

More information

CHAPTER 7 LEARNING. Jake Miller, Ocean Lakes High School

CHAPTER 7 LEARNING. Jake Miller, Ocean Lakes High School CHAPTER 7 LEARNING Jake Miller, Ocean Lakes High School Learning: Defined Learning: Relatively permanent change in [observable] behavior due to experience NOT temporary changes due to disease, injury,

More information

Evolution of Plastic Sensory-motor Coupling and Dynamic Categorization

Evolution of Plastic Sensory-motor Coupling and Dynamic Categorization Evolution of Plastic Sensory-motor Coupling and Dynamic Categorization Gentaro Morimoto and Takashi Ikegami Graduate School of Arts and Sciences The University of Tokyo 3-8-1 Komaba, Tokyo 153-8902, Japan

More information

Realization of Visual Representation Task on a Humanoid Robot

Realization of Visual Representation Task on a Humanoid Robot Istanbul Technical University, Robot Intelligence Course Realization of Visual Representation Task on a Humanoid Robot Emeç Erçelik May 31, 2016 1 Introduction It is thought that human brain uses a distributed

More information

Learning theory provides the basis for behavioral interventions. The USMLE behavioral science section always contains questions relating to learning

Learning theory provides the basis for behavioral interventions. The USMLE behavioral science section always contains questions relating to learning Learning theory provides the basis for behavioral interventions. The USMLE behavioral science section always contains questions relating to learning theory. Learning theory does not apply to behaviors

More information

TIME SERIES MODELING USING ARTIFICIAL NEURAL NETWORKS 1 P.Ram Kumar, 2 M.V.Ramana Murthy, 3 D.Eashwar, 4 M.Venkatdas

TIME SERIES MODELING USING ARTIFICIAL NEURAL NETWORKS 1 P.Ram Kumar, 2 M.V.Ramana Murthy, 3 D.Eashwar, 4 M.Venkatdas TIME SERIES MODELING USING ARTIFICIAL NEURAL NETWORKS 1 P.Ram Kumar, 2 M.V.Ramana Murthy, 3 D.Eashwar, 4 M.Venkatdas 1 Department of Computer Science & Engineering,UCE,OU,Hyderabad 2 Department of Mathematics,UCS,OU,Hyderabad

More information

Unmanned autonomous vehicles in air land and sea

Unmanned autonomous vehicles in air land and sea based on Gianni A. Di Caro lecture on ROBOT CONTROL RCHITECTURES SINGLE AND MULTI-ROBOT SYSTEMS: A CASE STUDY IN SWARM ROBOTICS Unmanned autonomous vehicles in air land and sea Robots and Unmanned Vehicles

More information

The organism s problem: Avoid predation and injury so you can reproduce

The organism s problem: Avoid predation and injury so you can reproduce Learning Chapter 7 Design a Brain The organism s problem: Avoid predation and injury so you can reproduce What characteristics are needed to behave adaptively and reproduce successfully? Consider: nearly

More information

I. Classical Conditioning

I. Classical Conditioning Learning Chapter 8 Learning A relatively permanent change in an organism that occur because of prior experience Psychologists must study overt behavior or physical changes to study learning Learning I.

More information

Chapter 1. Give an overview of the whole RL problem. Policies Value functions. Tic-Tac-Toe example

Chapter 1. Give an overview of the whole RL problem. Policies Value functions. Tic-Tac-Toe example Chapter 1 Give an overview of the whole RL problem n Before we break it up into parts to study individually Introduce the cast of characters n Experience (reward) n n Policies Value functions n Models

More information

CS 453X: Class 18. Jacob Whitehill

CS 453X: Class 18. Jacob Whitehill CS 453X: Class 18 Jacob Whitehill More on k-means Exercise: Empty clusters (1) Assume that a set of distinct data points { x (i) } are initially assigned so that none of the k clusters is empty. How can

More information

Intelligent Control Systems

Intelligent Control Systems Lecture Notes in 4 th Class in the Control and Systems Engineering Department University of Technology CCE-CN432 Edited By: Dr. Mohammed Y. Hassan, Ph. D. Fourth Year. CCE-CN432 Syllabus Theoretical: 2

More information

Memory, Attention, and Decision-Making

Memory, Attention, and Decision-Making Memory, Attention, and Decision-Making A Unifying Computational Neuroscience Approach Edmund T. Rolls University of Oxford Department of Experimental Psychology Oxford England OXFORD UNIVERSITY PRESS Contents

More information

This Lecture: Psychology of Memory and Brain Areas Involved

This Lecture: Psychology of Memory and Brain Areas Involved Lecture 18 (Nov 24 th ): LEARNING & MEMORY #1 Lecture Outline This Lecture: Psychology of Memory and Brain Areas Involved Next lecture: Neural Mechanisms for Memory 1) Psychology of Memory: Short Term

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

Neuroinformatics. Ilmari Kurki, Urs Köster, Jukka Perkiö, (Shohei Shimizu) Interdisciplinary and interdepartmental

Neuroinformatics. Ilmari Kurki, Urs Köster, Jukka Perkiö, (Shohei Shimizu) Interdisciplinary and interdepartmental Neuroinformatics Aapo Hyvärinen, still Academy Research Fellow for a while Post-docs: Patrik Hoyer and Jarmo Hurri + possibly international post-docs PhD students Ilmari Kurki, Urs Köster, Jukka Perkiö,

More information

Introduction to Physiological Psychology Review

Introduction to Physiological Psychology Review Introduction to Physiological Psychology Review ksweeney@cogsci.ucsd.edu www.cogsci.ucsd.edu/~ksweeney/psy260.html n Learning and Memory n Human Communication n Emotion 1 What is memory? n Working Memory:

More information

Auto-Encoder Pre-Training of Segmented-Memory Recurrent Neural Networks

Auto-Encoder Pre-Training of Segmented-Memory Recurrent Neural Networks Auto-Encoder Pre-Training of Segmented-Memory Recurrent Neural Networks Stefan Glüge, Ronald Böck and Andreas Wendemuth Faculty of Electrical Engineering and Information Technology Cognitive Systems Group,

More information

Butter Food Eat Sandwich Rye Jam Milk Flour Jelly Dough Crust Slice Wine Loaf Toast

Butter Food Eat Sandwich Rye Jam Milk Flour Jelly Dough Crust Slice Wine Loaf Toast Introduction to Physiological Psychology Learning and Memory ksweeney@cogsci.ucsd.edu cogsci.ucsd.edu/~ /~ksweeney/psy260.html Comments on your comments Thank you! Some things that I can change NOW: Slow

More information

Associative Learning

Associative Learning LEARNING Relatively permanent change in behavior Acquired from experience or observation Learning Associative Learning Observational Learning Classical Conditioning Operant Conditioning Associative Learning

More information

Time Experiencing by Robotic Agents

Time Experiencing by Robotic Agents Time Experiencing by Robotic Agents Michail Maniadakis 1 and Marc Wittmann 2 and Panos Trahanias 1 1- Foundation for Research and Technology - Hellas, ICS, Greece 2- Institute for Frontier Areas of Psychology

More information

Cell Responses in V4 Sparse Distributed Representation

Cell Responses in V4 Sparse Distributed Representation Part 4B: Real Neurons Functions of Layers Input layer 4 from sensation or other areas 3. Neocortical Dynamics Hidden layers 2 & 3 Output layers 5 & 6 to motor systems or other areas 1 2 Hierarchical Categorical

More information

Cerebral Cortex. Edmund T. Rolls. Principles of Operation. Presubiculum. Subiculum F S D. Neocortex. PHG & Perirhinal. CA1 Fornix CA3 S D

Cerebral Cortex. Edmund T. Rolls. Principles of Operation. Presubiculum. Subiculum F S D. Neocortex. PHG & Perirhinal. CA1 Fornix CA3 S D Cerebral Cortex Principles of Operation Edmund T. Rolls F S D Neocortex S D PHG & Perirhinal 2 3 5 pp Ento rhinal DG Subiculum Presubiculum mf CA3 CA1 Fornix Appendix 4 Simulation software for neuronal

More information

This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research and

This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research and This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research and education use, including for instruction at the authors institution

More information

Classical Conditioning Classical Conditioning - a type of learning in which one learns to link two stimuli and anticipate events.

Classical Conditioning Classical Conditioning - a type of learning in which one learns to link two stimuli and anticipate events. Classical Conditioning Classical Conditioning - a type of learning in which one learns to link two stimuli and anticipate events. behaviorism - the view that psychology (1) should be an objective science

More information

CHAPTER I From Biological to Artificial Neuron Model

CHAPTER I From Biological to Artificial Neuron Model CHAPTER I From Biological to Artificial Neuron Model EE543 - ANN - CHAPTER 1 1 What you see in the picture? EE543 - ANN - CHAPTER 1 2 Is there any conventional computer at present with the capability of

More information

Reactive agents and perceptual ambiguity

Reactive agents and perceptual ambiguity Major theme: Robotic and computational models of interaction and cognition Reactive agents and perceptual ambiguity Michel van Dartel and Eric Postma IKAT, Universiteit Maastricht Abstract Situated and

More information

Outline. History of Learning Theory. Pavlov s Experiment: Step 1. Associative learning 9/26/2012. Nature or Nurture

Outline. History of Learning Theory. Pavlov s Experiment: Step 1. Associative learning 9/26/2012. Nature or Nurture Outline What is learning? Associative Learning Classical Conditioning Operant Conditioning Observational Learning History of Learning Theory Nature or Nurture BEHAVIORISM Tabula Rasa Learning: Systematic,

More information

Multi-Associative Memory in flif Cell Assemblies

Multi-Associative Memory in flif Cell Assemblies Multi-Associative Memory in flif Cell Assemblies Christian R. Huyck (c.huyck@mdx.ac.uk) Kailash Nadh (k.nadh@mdx.ac.uk) School of Engineering and Information Sciences Middlesex University London, UK Abstract

More information

PMR5406 Redes Neurais e Lógica Fuzzy. Aula 5 Alguns Exemplos

PMR5406 Redes Neurais e Lógica Fuzzy. Aula 5 Alguns Exemplos PMR5406 Redes Neurais e Lógica Fuzzy Aula 5 Alguns Exemplos APPLICATIONS Two examples of real life applications of neural networks for pattern classification: RBF networks for face recognition FF networks

More information

Institute of Psychology C.N.R. - Rome. Using emergent modularity to develop control systems for mobile robots

Institute of Psychology C.N.R. - Rome. Using emergent modularity to develop control systems for mobile robots Institute of Psychology C.N.R. - Rome Using emergent modularity to develop control systems for mobile robots Stefano Nolfi Institute of Psychology, National Research Council, Rome, Italy. e-mail: stefano@kant.irmkant.rm.cnr.it

More information

Motor primitive and sequence self-organization in a hierarchical recurrent neural network

Motor primitive and sequence self-organization in a hierarchical recurrent neural network Neural Networks 17 (2004) 1291 1309 2004 Special Issue Motor primitive and sequence self-organization in a hierarchical recurrent neural network Rainer W. Paine*, Jun Tani Laboratory for Behavior and Dynamic

More information

196 IEEE TRANSACTIONS ON AUTONOMOUS MENTAL DEVELOPMENT, VOL. 2, NO. 3, SEPTEMBER 2010

196 IEEE TRANSACTIONS ON AUTONOMOUS MENTAL DEVELOPMENT, VOL. 2, NO. 3, SEPTEMBER 2010 196 IEEE TRANSACTIONS ON AUTONOMOUS MENTAL DEVELOPMENT, VOL. 2, NO. 3, SEPTEMBER 2010 Top Down Gaze Movement Control in Target Search Using Population Cell Coding of Visual Context Jun Miao, Member, IEEE,

More information

Introduction and Historical Background. August 22, 2007

Introduction and Historical Background. August 22, 2007 1 Cognitive Bases of Behavior Introduction and Historical Background August 22, 2007 2 Cognitive Psychology Concerned with full range of psychological processes from sensation to knowledge representation

More information

Genetic Algorithms and their Application to Continuum Generation

Genetic Algorithms and their Application to Continuum Generation Genetic Algorithms and their Application to Continuum Generation Tracy Moore, Douglass Schumacher The Ohio State University, REU, 2001 Abstract A genetic algorithm was written to aid in shaping pulses

More information

Classical Conditioning. Learning. Classical conditioning terms. Classical Conditioning Procedure. Procedure, cont. Important concepts

Classical Conditioning. Learning. Classical conditioning terms. Classical Conditioning Procedure. Procedure, cont. Important concepts Learning Classical Conditioning Pavlov study of digestion dogs salivate before getting food learning as signal detection: emphasis on what happens before a given behavior Classical conditioning terms Stimulus:

More information

Contents. Just Classifier? Rules. Rules: example. Classification Rule Generation for Bioinformatics. Rule Extraction from a trained network

Contents. Just Classifier? Rules. Rules: example. Classification Rule Generation for Bioinformatics. Rule Extraction from a trained network Contents Classification Rule Generation for Bioinformatics Hyeoncheol Kim Rule Extraction from Neural Networks Algorithm Ex] Promoter Domain Hybrid Model of Knowledge and Learning Knowledge refinement

More information

ENVIRONMENTAL REINFORCEMENT LEARNING: A Real-time Learning Architecture for Primitive Behavior Refinement

ENVIRONMENTAL REINFORCEMENT LEARNING: A Real-time Learning Architecture for Primitive Behavior Refinement ENVIRONMENTAL REINFORCEMENT LEARNING: A Real-time Learning Architecture for Primitive Behavior Refinement TaeHoon Anthony Choi, Eunbin Augustine Yim, and Keith L. Doty Machine Intelligence Laboratory Department

More information

Combining associative learning and nonassociative learning to achieve robust reactive navigation in mobile robots

Combining associative learning and nonassociative learning to achieve robust reactive navigation in mobile robots Combining associative learning and nonassociative learning to achieve robust reactive navigation in mobile robots Carolina Chang cchang@ldc.usb.ve Grupo de Inteligencia Artificial, Departamento de Computación

More information

Connectionism and Classical Conditioning

Connectionism and Classical Conditioning Connectionism and Classical Conditioning Michael R.W. Dawson University of Alberta Edmonton, Alberta Canada T6G 2P9 1-(780)-492-5175 Abstract The purpose of this monograph is to examine the relationship

More information

PSY 315 Lecture 13 (3/7/2011) (Learning & Memory Mechanics) Dr. Achtman PSY 215

PSY 315 Lecture 13 (3/7/2011) (Learning & Memory Mechanics) Dr. Achtman PSY 215 PSY 215 Lecture 13 Topic: Learning & Memory- Mechanics Chapter 13.2, pages 393-399 Announcements: Question #37 was removed from Exam 2 and all students will receive an additional point. Average grade on

More information

Conditioning and Concept Formation in Embodied Agents

Conditioning and Concept Formation in Embodied Agents From: AAAI Technical Report SS-01-05. Compilation copyright 2001, AAAI (www.aaai.org). All rights reserved. Conditioning and Concept Formation in Embodied Agents Terry Stewart Institute of Interdisciplinary

More information

A model to explain the emergence of reward expectancy neurons using reinforcement learning and neural network $

A model to explain the emergence of reward expectancy neurons using reinforcement learning and neural network $ Neurocomputing 69 (26) 1327 1331 www.elsevier.com/locate/neucom A model to explain the emergence of reward expectancy neurons using reinforcement learning and neural network $ Shinya Ishii a,1, Munetaka

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

Using stigmergy to incorporate the time into artificial neural networks

Using stigmergy to incorporate the time into artificial neural networks Using stigmergy to incorporate the time into artificial neural networks Federico A. Galatolo, Mario G.C.A. Cimino, and Gigliola Vaglini Department of Information Engineering, University of Pisa, 56122

More information

CHAPTER 6. Learning. Lecture Overview. Introductory Definitions PSYCHOLOGY PSYCHOLOGY PSYCHOLOGY

CHAPTER 6. Learning. Lecture Overview. Introductory Definitions PSYCHOLOGY PSYCHOLOGY PSYCHOLOGY Learning CHAPTER 6 Write down important terms in this video. Explain Skinner s view on Free Will. Lecture Overview Classical Conditioning Operant Conditioning Cognitive-Social Learning The Biology of Learning

More information

Design of an Optimized Fuzzy Classifier for the Diagnosis of Blood Pressure with a New Computational Method for Expert Rule Optimization

Design of an Optimized Fuzzy Classifier for the Diagnosis of Blood Pressure with a New Computational Method for Expert Rule Optimization algorithms Article Design of an Optimized Fuzzy Classifier for the Diagnosis of Blood Pressure with a New Computational Method for Expert Rule Optimization Juan Carlos Guzman 1, Patricia Melin 1, * ID

More information

Evolving Imitating Agents and the Emergence of a Neural Mirror System

Evolving Imitating Agents and the Emergence of a Neural Mirror System Evolving Imitating Agents and the Emergence of a Neural Mirror System Elhanan Borenstein and Eytan Ruppin,2 School of Computer Science, Tel Aviv University, Tel-Aviv 6998, Israel 2 School of Medicine,

More information

NEURAL SYSTEMS FOR INTEGRATING ROBOT BEHAVIOURS

NEURAL SYSTEMS FOR INTEGRATING ROBOT BEHAVIOURS NEURAL SYSTEMS FOR INTEGRATING ROBOT BEHAVIOURS Brett Browning & Gordon Wyeth University of Queensland Computer Science and Electrical Engineering Department Email: browning@elec.uq.edu.au & wyeth@elec.uq.edu.au

More information

Unit 6 Learning.

Unit 6 Learning. Unit 6 Learning https://www.apstudynotes.org/psychology/outlines/chapter-6-learning/ 1. Overview 1. Learning 1. A long lasting change in behavior resulting from experience 2. Classical Conditioning 1.

More information

AU B. Sc.(Hon's) (Fifth Semester) Esamination, Introduction to Artificial Neural Networks-IV. Paper : -PCSC-504

AU B. Sc.(Hon's) (Fifth Semester) Esamination, Introduction to Artificial Neural Networks-IV. Paper : -PCSC-504 AU-6919 B. Sc.(Hon's) (Fifth Semester) Esamination, 2014 Introduction to Artificial Neural Networks-IV Paper : -PCSC-504 Section-A 1. (I) Synaptic Weights provides the... method for the design of neural

More information

UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Final, Fall 2014

UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Final, Fall 2014 UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Final, Fall 2014 Exam policy: This exam allows two one-page, two-sided cheat sheets (i.e. 4 sides); No other materials. Time: 2 hours. Be sure to write

More information

Classical Conditioning & Operant Conditioning

Classical Conditioning & Operant Conditioning Classical Conditioning & Operant Conditioning What is Classical Conditioning? Learning Objective: Students will be able to describe the difference between Classical and Operant Conditioning. How Do We

More information

University of Cambridge Engineering Part IB Information Engineering Elective

University of Cambridge Engineering Part IB Information Engineering Elective University of Cambridge Engineering Part IB Information Engineering Elective Paper 8: Image Searching and Modelling Using Machine Learning Handout 1: Introduction to Artificial Neural Networks Roberto

More information

Dikran J. Martin Introduction to Psychology

Dikran J. Martin Introduction to Psychology Dikran J. Martin Introduction to Psychology Name: Date: Lecture Series: Chapter 7 Learning Pages: 32 TEXT: Lefton, Lester A. and Brannon, Linda (2003). PSYCHOLOGY. (Eighth Edition.) Needham Heights, MA:

More information

Chapter 7 - Learning

Chapter 7 - Learning Chapter 7 - Learning How Do We Learn Classical Conditioning Operant Conditioning Observational Learning Defining Learning Learning a relatively permanent change in an organism s behavior due to experience.

More information

Oxford Foundation for Theoretical Neuroscience and Artificial Intelligence

Oxford Foundation for Theoretical Neuroscience and Artificial Intelligence Oxford Foundation for Theoretical Neuroscience and Artificial Intelligence Oxford Foundation for Theoretical Neuroscience and Artificial Intelligence For over two millennia, philosophers and scientists

More information

Model-Based fmri Analysis. Will Alexander Dept. of Experimental Psychology Ghent University

Model-Based fmri Analysis. Will Alexander Dept. of Experimental Psychology Ghent University Model-Based fmri Analysis Will Alexander Dept. of Experimental Psychology Ghent University Motivation Models (general) Why you ought to care Model-based fmri Models (specific) From model to analysis Extended

More information

Learning Ashrakat & Roukaya. For reference open pages 50-57

Learning Ashrakat & Roukaya. For reference open pages 50-57 Learning Ashrakat & Roukaya For reference open pages 50-57 Learning Objectives 1. What learning is 2. the different types of learning 3. Learn about each type a. Conditioned Learning (Classical & Operant)

More information

Unit 06 - Overview. Click on the any of the above hyperlinks to go to that section in the presentation.

Unit 06 - Overview. Click on the any of the above hyperlinks to go to that section in the presentation. Unit 06 - Overview How We Learn and Classical Conditioning Operant Conditioning Operant Conditioning s Applications, and Comparison to Classical Conditioning Biology, Cognition, and Learning Learning By

More information

Cognitive Modelling Themes in Neural Computation. Tom Hartley

Cognitive Modelling Themes in Neural Computation. Tom Hartley Cognitive Modelling Themes in Neural Computation Tom Hartley t.hartley@psychology.york.ac.uk Typical Model Neuron x i w ij x j =f(σw ij x j ) w jk x k McCulloch & Pitts (1943), Rosenblatt (1957) Net input:

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

Psychology in Your Life

Psychology in Your Life Sarah Grison Todd Heatherton Michael Gazzaniga Psychology in Your Life FIRST EDITION Chapter 6 Learning 2014 W. W. Norton & Company, Inc. Section 6.1 How Do the Parts of Our Brains Function? 6.1 What Are

More information

Brief History of Work in the area of Learning and Memory

Brief History of Work in the area of Learning and Memory Brief History of Work in the area of Learning and Memory Basic Questions how does memory work are there different kinds of memory what is their logic where in the brain do we learn where do we store what

More information