Learning and Adaptive Behavior, Part II

Size: px
Start display at page:

Download "Learning and Adaptive Behavior, Part II"

Transcription

1 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

2 A Challenge: Getting RL to Work on Real Robots When is learning appropriate? When task is originally under-specified or difficult to code exactly by hand When task has parameters that are likely to change over time in unpredictable ways When time taken to learn control policy is less than that for hand-coding a comparable policy When learned policy can be executed more efficiently than a hand-coded one

3 Problems with RL on Robots Huge number of states to explore, with large number of possible actions in each state. E.g., 24 sonar sensors, quantized into 3 range bands 282 billion possible states If possible actions in each state or go forwards or backwards > 560 billion state-action combinations to try Robot is physical, thus it takes time to perform an action 1 second per action 20,000 years to try each combination During early learning, robot s actions may be dangerous Let s try rolling down the stairwell to see what next state I end up in One possible safeguard: give robot reflexes to stop dangerous actions

4 One Possible Framework for RL on Robots 3 components: Provided system, with initial control policy and immediate reward function Policy learning process Value learning process Policy learner + value learner Q(s,a) Initial control policy next state action Reward Environment

5 Fundamental Issues Quick learning: learn in real-time Generalization: take what is known and hypothesize about unknown/unvisited states Shifting functions: adapt over time

6 Other Examples of Reinforcmenet Learning: Model-Based Reinforcement Learning QuickTime and a Sorenson Video decompressor are needed to see this picture. QuickTime and a Sorenson Video decompressor are needed to see this picture.

7 Another Related Example: Imitation Learning QuickTime and a Sorenson Video decompressor are needed to see this picture.

8 Two New Topics: Objectives To understand neural network learning applied to robotics To understand genetic algorithms applied to robotics

9 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.. w 1 w 2 w 3.. Neuron Σ θ Output.. x n w n Synaptic weights

10 Neural Net Quick Background (con t.) 1960s 1970s: neural net research in decline due to Minsky and Papert book (1969) that proved limitations of single-layer perceptron networks 1980s: resurgence due to multi-layer neural networks and use of backpropogation 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

11 Methods for Encoding Behavior-Based Robotic Control in Neural Networks Hebbian Learning Perceptron Learning Classical Conditioning Adaptive Heuristic Critic Learning

12 1. Hebbian Learning Hebb (1949) developed one of earliest training algorithms for neural networks Hebbian learning: 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 and o j are the outputs of neurons i and j, respectively

13 2. 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.

14 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 and o j are the correct and incorrect outputs, respectively The Delta rule strives to minimize the error term using a gradient descent approach

15 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

16 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 and o j are the correct and incorrect outputs, respectively The errors are propagated backward from the output layer.

17 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 NOTE: Hebbian learning can also produce classical conditioning Ivan Pavlov

18 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

19 Robot Example of Classical Conditioning Studies of Vershure, et al (1992) for collision avoidance and target acquisition Divide positive unconditioned stimulus (US) into 4 discrete areas in which attractive (appetitive) target may appear: ahead behind left right Unconditioned response (UR) set consists of 6 possible commands: advance reverse turn right 9 degrees turn right 1 degree turn left 9 degrees turn left 1 degree Two additional collision sensors serve as negative US, producing a response consisting of a reverse and turning 9 degrees away from direction of collision Negative US can inhibit positive US, to ensure that managing collisions is first priority

20 Robot example (con t.) CSs: use range sensor that produces distance profile of 180 degrees in direction robot is heading Readings divided into varying, discrete levels of resolution: Forward (ranging from 30 to +30): 20 units covering 3 degrees each Area to right (+30 to +60): 5 units covering 6 degrees each Area to far right (+60 to +90): 3 units covering 10 degrees each Left side: analogous to right Total range readings: 36 units

21 Robot example (con t.) For neural network implementation, perceptron-like linear threshold units with binary activation values are used Synaptic weights updated according to following rule: (w ij ) = (1/N) x (ηo i o j εοw ij ) where η is the learning rate ε is the decay rate N is the number of units in the CS field o i, o j is the binary output value of units i and j, respectively, and o is the average activity of the US field

22 Robot example (con t.) Robot s task: learn useful behaviors by associating perceptual stimuli with environmental feedback Behaviors include: avoidance, where robot learns not to bump into things approach, to desired target Note that robot has no a priori understanding of how to use range data to prevent collisions from occurring in the US set; this must be learned from the CS Simulation studies: indicate that successful behavior does occur in a manner consistent with agent s goals

23 Other Examples of Robot Learning Using Classical Conditioning Others have shown similar technique useful for learning: Sorting colored blocks that conduct electricity (either strongly or weakly) based on feedback from an aversive or appetitive response Teaching a Braitenberg-like robot, consisting of a neural net of 5 neurons, to seek light Teaching robot to develop a topological map using a neural network, by learning suitable responses at different locations in the world Robot learning of encodings similar to potential fields for representing learned landmark positions

24 Example of RL Learning (+Neural Nets) (Movies) QuickTime and a Cinepak decompressor are needed to see this picture. Khepera robot QuickTime and a Cinepak decompressor are needed to see this picture.

25 4. Connectionist Adaptive Heuristic Critic Learning (AHC) With connectionist adaptive heuristic critic (AHC) reinforcement learning methods, a critic learns the utility or value of particular states through reinforcement Learned values are then used locally to reinforce the selection of particular actions for a given state Gachet, et al (1994) use this approach as basis for learning relative strengths (i.e., gain matrix G) of each behavior s response within an active assemblage Specific goals of this study: Learn how to effectively coordinate a robot equipped with the following behaviors: goal attraction two perimeter-following behaviors (left and right) free-space attraction avoiding objects following a path Output for each behavior is a vector that the robot sums before execution (a la schema methods we have studied)

26 Connectionist AHC Learning System Weight Matrix V Adaptive Critic Element Reinforcement Signal Local Reinforcement Signals from Critic Sensor Data Classification System Input Layer Weight Matrix W Adaptive Search Element Output Behavioral Gains

27 AHC network (con t) AHC Network starts with classification system that maps incoming sonar data onto a set of situations (either 32 or 64, depending on the task) that reflect the sensed environment Output layer containing a weight matrix W, called the associative search element (ASE) computes individual behavioral gains for each behavior: W ki (t+1) = W ki (t) + αb i (t)e ki (t) where α is learning rate and e ki (t) is eligibility of weight W ki for reinforcement Adaptive critic element (ACE) determines reinforcement signal to be applied to the ASE ACE s weights V are updated independently: V ki (t+1) = V ki (t) + βb i (t)x k (t) where β is positive constant and X k is eligibility for the ACE This partitioning of reinforcement updating rules from action element updating is a characteristic of AHC methods in general

28 AHC Example (con t.) Task for robot: learn set of gain multipliers (G) for a particular task-environment Three different missions: learning to explore environment safely learning how to move back and forth between alternating goal points safely follow a predetermined path without collisions During exploration: Robot moves randomly When collision occurs, negative reinforcement applied and robot moved back to a position it occupied N steps earlier (N = 30 for simulation, 10 for physical robot) For goal-oriented missions, negative reinforcement occurs when collision is imminent, and when robot is pointing away from goal (or path) and no obstacles are blocking its way to the goal Experimentations showed learning approach successful for these tasks

29 Summary of neural network learning Neural networks, a form of reinforcement learning, use specialized, multi-node architectures. Learning in neural nets occurs through the adjustment of synaptic weights by an error minimization procedure, such as: Hebb s rule Back Propagation Classical conditioning in which a conditioned stimulus is eventually associated with an unconditioned response can be manifested in robotic systems

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

Lesson 6 Learning II Anders Lyhne Christensen, D6.05, INTRODUCTION TO AUTONOMOUS MOBILE ROBOTS Lesson 6 Learning II Anders Lyhne Christensen, D6.05, anders.christensen@iscte.pt INTRODUCTION TO AUTONOMOUS MOBILE ROBOTS First: Quick Background in Neural Nets Some of earliest work in neural networks

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Katsunari Shibata and Tomohiko Kawano

Katsunari Shibata and Tomohiko Kawano Learning of Action Generation from Raw Camera Images in a Real-World-Like Environment by Simple Coupling of Reinforcement Learning and a Neural Network Katsunari Shibata and Tomohiko Kawano Oita University,

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

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

Conditioning and Learning. Chapter 7

Conditioning and Learning. Chapter 7 Conditioning and Learning Chapter 7 Learning is knowledge of skills acquired by instruction or studying. It is a permanent change in behavior due to reinforcement. Reinforcement refers to any event that

More information

Bronze statue of Pavlov and one of his dogs located on the grounds of his laboratory at Koltushi Photo taken by Jackie D. Wood, June 2004.

Bronze statue of Pavlov and one of his dogs located on the grounds of his laboratory at Koltushi Photo taken by Jackie D. Wood, June 2004. Ivan Pavlov http://physiologyonline.physiology.org/ cgi/content/full/19/6/326 Bronze statue of Pavlov and one of his dogs located on the grounds of his laboratory at Koltushi Photo taken by Jackie D. Wood,

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

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

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

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

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

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

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

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

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

Learning. AP PSYCHOLOGY Unit 4

Learning. AP PSYCHOLOGY Unit 4 Learning AP PSYCHOLOGY Unit 4 Learning Learning is a lasting change in behavior or mental process as the result of an experience. There are two important parts: a lasting change a simple reflexive reaction

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

Learning. AP PSYCHOLOGY Unit 5

Learning. AP PSYCHOLOGY Unit 5 Learning AP PSYCHOLOGY Unit 5 Learning Learning is a lasting change in behavior or mental process as the result of an experience. There are two important parts: a lasting change a simple reflexive reaction

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

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

PSYCHOLOGY. Chapter 6 LEARNING PowerPoint Image Slideshow

PSYCHOLOGY. Chapter 6 LEARNING PowerPoint Image Slideshow PSYCHOLOGY Chapter 6 LEARNING PowerPoint Image Slideshow Learning? What s that? A relatively permanent change in behavior brought about by experience or practice. Note that learning is NOT the same as

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

1. A type of learning in which behavior is strengthened if followed by a reinforcer or diminished if followed by a punisher.

1. A type of learning in which behavior is strengthened if followed by a reinforcer or diminished if followed by a punisher. 1. A stimulus change that increases the future frequency of behavior that immediately precedes it. 2. In operant conditioning, a reinforcement schedule that reinforces a response only after a specified

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

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

New Ideas for Brain Modelling

New Ideas for Brain Modelling IOSR Journal of Engineering (IOSRJEN) ISSN (e): 2250-3021, ISSN (p): 2278-8719 Vol. 06, Issue10 (Oct. 2016), V1 PP 13-17 www.iosrjen.org New Ideas for Brain Modelling Kieran Greer 1 1 Distributed Computing

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 5: How Do We Learn?

Chapter 5: How Do We Learn? Chapter 5: How Do We Learn? Defining Learning A relatively permanent change in behavior or the potential for behavior that results from experience Results from many life experiences, not just structured

More information

Learning Utility for Behavior Acquisition and Intention Inference of Other Agent

Learning Utility for Behavior Acquisition and Intention Inference of Other Agent Learning Utility for Behavior Acquisition and Intention Inference of Other Agent Yasutake Takahashi, Teruyasu Kawamata, and Minoru Asada* Dept. of Adaptive Machine Systems, Graduate School of Engineering,

More information

How has Computational Neuroscience been useful? Virginia R. de Sa Department of Cognitive Science UCSD

How has Computational Neuroscience been useful? Virginia R. de Sa Department of Cognitive Science UCSD How has Computational Neuroscience been useful? 1 Virginia R. de Sa Department of Cognitive Science UCSD What is considered Computational Neuroscience? 2 What is considered Computational Neuroscience?

More information

Chapter 6. Learning: The Behavioral Perspective

Chapter 6. Learning: The Behavioral Perspective Chapter 6 Learning: The Behavioral Perspective 1 Can someone have an asthma attack without any particles in the air to trigger it? Can an addict die of a heroin overdose even if they ve taken the same

More information

ANN predicts locoregional control using molecular marker profiles of. Head and Neck squamous cell carcinoma

ANN predicts locoregional control using molecular marker profiles of. Head and Neck squamous cell carcinoma ANN predicts locoregional control using molecular marker profiles of Head and Neck squamous cell carcinoma Final Project: 539 Dinesh Kumar Tewatia Introduction Radiotherapy alone or combined with chemotherapy,

More information

Associative Learning

Associative Learning Learning Learning Associative Learning Classical Conditioning Operant Conditioning Observational Learning Biological Components of Learning Cognitive Components of Learning Behavioral Therapies Associative

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

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

A Reinforcement Learning Approach Involving a Shortest Path Finding Algorithm

A Reinforcement Learning Approach Involving a Shortest Path Finding Algorithm Proceedings of the 003 IEEE/RSJ Intl. Conference on Intelligent Robots and Systems Proceedings Las Vegas, of Nevada the 003 October IEEE/RSJ 003 Intl. Conference on Intelligent Robots and Systems Las Vegas,

More information

Chapter 7. Learning From Experience

Chapter 7. Learning From Experience Learning From Experience Psychology, Fifth Edition, James S. Nairne What s It For? Learning From Experience Noticing and Ignoring Learning What Events Signal Learning About the Consequences of Our Behavior

More information

PART - A 1. Define Artificial Intelligence formulated by Haugeland. The exciting new effort to make computers think machines with minds in the full and literal sense. 2. Define Artificial Intelligence

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

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

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

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

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

CS 182 Midterm review

CS 182 Midterm review CS 182 Midterm review Near far Image schemas What is a schema? a pattern capturing structure in the world What is an image schema? a schema about interaction with the world Can you name some? Containment

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

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

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 Machine Learning. Katherine Heller Deep Learning Summer School 2018

Introduction to Machine Learning. Katherine Heller Deep Learning Summer School 2018 Introduction to Machine Learning Katherine Heller Deep Learning Summer School 2018 Outline Kinds of machine learning Linear regression Regularization Bayesian methods Logistic Regression Why we do this

More information

The Re(de)fined Neuron

The Re(de)fined Neuron The Re(de)fined Neuron Kieran Greer, Distributed Computing Systems, Belfast, UK. http://distributedcomputingsystems.co.uk Version 1.0 Abstract This paper describes a more biologically-oriented process

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

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

COMP9444 Neural Networks and Deep Learning 5. Convolutional Networks

COMP9444 Neural Networks and Deep Learning 5. Convolutional Networks COMP9444 Neural Networks and Deep Learning 5. Convolutional Networks Textbook, Sections 6.2.2, 6.3, 7.9, 7.11-7.13, 9.1-9.5 COMP9444 17s2 Convolutional Networks 1 Outline Geometry of Hidden Unit Activations

More information

The Rescorla Wagner Learning Model (and one of its descendants) Computational Models of Neural Systems Lecture 5.1

The Rescorla Wagner Learning Model (and one of its descendants) Computational Models of Neural Systems Lecture 5.1 The Rescorla Wagner Learning Model (and one of its descendants) Lecture 5.1 David S. Touretzky Based on notes by Lisa M. Saksida November, 2015 Outline Classical and instrumental conditioning The Rescorla

More information

acquisition associative learning behaviorism A type of learning in which one learns to link two or more stimuli and anticipate events

acquisition associative learning behaviorism A type of learning in which one learns to link two or more stimuli and anticipate events 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

3/7/2010. Theoretical Perspectives

3/7/2010. Theoretical Perspectives Theoretical Perspectives REBT (1955) Albert Ellis Action & Result Oriented Teaches how to identify self-defeating thoughts Replaces thoughts w/ life enhancing ones 1 A B C s of personality formation: A

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

PSY380: VISION SCIENCE

PSY380: VISION SCIENCE PSY380: VISION SCIENCE 1) Questions: - Who are you and why are you here? (Why vision?) - What is visual perception? - What is the function of visual perception? 2) The syllabus & instructor 3) Lecture

More information

Robot Behavior Genghis, MIT Callisto, GATech

Robot Behavior Genghis, MIT Callisto, GATech Robot Behavior Genghis, MIT Callisto, GATech Today s Objectives To learn what robotic behaviors are To obtain a basic understanding of the design approaches related to behavior-based robotic systems To

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

THEORIES OF PERSONALITY II

THEORIES OF PERSONALITY II THEORIES OF PERSONALITY II THEORIES OF PERSONALITY II Learning Theory SESSION 8 2014 [Type the abstract of the document here. The abstract is typically a short summary of the contents of the document.

More information

Active Sites model for the B-Matrix Approach

Active Sites model for the B-Matrix Approach Active Sites model for the B-Matrix Approach Krishna Chaithanya Lingashetty Abstract : This paper continues on the work of the B-Matrix approach in hebbian learning proposed by Dr. Kak. It reports the

More information

Information Processing During Transient Responses in the Crayfish Visual System

Information Processing During Transient Responses in the Crayfish Visual System Information Processing During Transient Responses in the Crayfish Visual System Christopher J. Rozell, Don. H. Johnson and Raymon M. Glantz Department of Electrical & Computer Engineering Department of

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

Learning. 3. Which of the following is an example of a generalized reinforcer? (A) chocolate cake (B) water (C) money (D) applause (E) high grades

Learning. 3. Which of the following is an example of a generalized reinforcer? (A) chocolate cake (B) water (C) money (D) applause (E) high grades Learning Practice Questions Each of the questions or incomplete statements below is followed by five suggested answers or completions. Select the one that is best in each case. 1. Just before something

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

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

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

Chapter 1: Behaviorism and the beginning of cognitive science

Chapter 1: Behaviorism and the beginning of cognitive science Chapter 1: Behaviorism and the beginning of cognitive science Steps towards cognitive science The cognitive turn in psychology (away from behaviorism) Developments in the theory of computation and theory

More information

Agents and Environments

Agents and Environments Agents and Environments Berlin Chen 2004 Reference: 1. S. Russell and P. Norvig. Artificial Intelligence: A Modern Approach. Chapter 2 AI 2004 Berlin Chen 1 What is an Agent An agent interacts with its

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

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

Learning. Association. Association. Unit 6: Learning. Learning. Classical or Pavlovian Conditioning. Different Types of Learning

Learning. Association. Association. Unit 6: Learning. Learning. Classical or Pavlovian Conditioning. Different Types of Learning Unit 6: Learning Learning Learning relatively permanent change in an organism s behavior due to experience experience (nurture) is the key to learning Different Types of Learning Classical -learn by association

More information

Reward-Modulated Hebbian Learning of Decision Making

Reward-Modulated Hebbian Learning of Decision Making ARTICLE Communicated by Laurenz Wiskott Reward-Modulated Hebbian Learning of Decision Making Michael Pfeiffer pfeiffer@igi.tugraz.at Bernhard Nessler nessler@igi.tugraz.at Institute for Theoretical Computer

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

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

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

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

CAS Seminar - Spiking Neurons Network (SNN) Jakob Kemi ( )

CAS Seminar - Spiking Neurons Network (SNN) Jakob Kemi ( ) CAS Seminar - Spiking Neurons Network (SNN) Jakob Kemi (820622-0033) kemiolof@student.chalmers.se November 20, 2006 Introduction Biological background To be written, lots of good sources. Background First

More information

PSYC 337 LEARNING. Session 3 Classical Conditioning. Lecturer: Dr. Inusah Abdul-Nasiru Contact Information:

PSYC 337 LEARNING. Session 3 Classical Conditioning. Lecturer: Dr. Inusah Abdul-Nasiru Contact Information: PSYC 337 LEARNING Session 3 Classical Conditioning Lecturer: Dr. Inusah Abdul-Nasiru Contact Information: iabdul-nasiru@ug.edu.gh College of Education School of Continuing and Distance Education 2014/2015

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

Learning = an enduring change in behavior, resulting from experience.

Learning = an enduring change in behavior, resulting from experience. Chapter 6: Learning Learning = an enduring change in behavior, resulting from experience. Conditioning = a process in which environmental stimuli and behavioral processes become connected Two types of

More information