Evolutionary Approach to Investigations of Cognitive Systems Vladimir Red ’ ko a), Anton Koval ’ b) a) Scientific Research Institute for System Analysis,

Slides:



Advertisements
Similar presentations
Approaches, Tools, and Applications Islam A. El-Shaarawy Shoubra Faculty of Eng.
Advertisements

The Logic of Intelligence Pei Wang Department of Computer and Information Sciences Temple University.
Neural Representation, Embodied and Evolved Pete Mandik Chairman, Department of Philosophy Coordinator, Cognitive Science Laboratory William Paterson University,
An Introduction to Artificial Intelligence Presented by : M. Eftekhari.
4 Intelligent Systems.
1 OSCAR: An Architecture for Generally Intelligent Agents John L. Pollock Philosophy and Cognitive Science University of Arizona
Autopoietic Theory Self-organization. or Exploring the science of wholeness that nurtures the human spirit.
Chapter 4 DECISION SUPPORT AND ARTIFICIAL INTELLIGENCE
6/2/2001 Cooperative Agent Systems: Artificial Agents Play the Ultimatum Game Steven O. Kimbrough Presented at FMEC 2001, Oslo Joint work with Fang Zhong.
XYZ 6/18/2015 MIT Brain and Cognitive Sciences Convergence Analysis of Reinforcement Learning Agents Srinivas Turaga th March, 2004.
An Introduction to Black-Box Complexity
Marakas: Decision Support Systems, 2nd Edition © 2003, Prentice-Hall Chapter Chapter 7: Expert Systems and Artificial Intelligence Decision Support.
Simulation Models as a Research Method Professor Alexander Settles.
Towards A Multi-Agent System for Network Decision Analysis Jan Dijkstra.
The History and Methods of Cognitive Psychology. What is Cognitive Psychology? The branch of psychology that studies how we perceive, attend, recognize,
Introduction There are three major scientific research methods that are used to study the theories of Second Language Acquisition (SLA). These three methods.
C463 / B551 Artificial Intelligence Dana Vrajitoru Introduction.
Artificial Intelligence By Ryan Shoultes & Jeremy Creighton.
컴퓨터 그래픽스 분야의 캐릭터 자동생성을 위하여 인공생명의 여러 가지 방법론이 어떻게 적용될 수 있는지 이해
COGNITIVE RADIO FOR NEXT-GENERATION WIRELESS NETWORKS: AN APPROACH TO OPPORTUNISTIC CHANNEL SELECTION IN IEEE BASED WIRELESS MESH Dusit Niyato,
THE NEW ERA OF LIFE. Introduction: Artificial Intelligence (AI) is the area of computer science focusing on creating machines that can engage on behaviors.
Chapter 11: Artificial Intelligence
The Role of Artificial Life, Cellular Automata and Emergence in the study of Artificial Intelligence Ognen Spiroski CITY Liberal Studies 2005.
Chapter 14: Artificial Intelligence Invitation to Computer Science, C++ Version, Third Edition.
Psychology Elyria Catholic High School Mr. Malbasa.
Laws of Logic and Rules of Evidence Larry Knop Hamilton College.
Structuralism and Functionalism
Computational Investigations of the Regulative Role of Pleasure in Adaptive Behavior Action-Selection Biased by Pleasure-Regulated Simulated Interaction.
Biology I.  Biology offers a framework to pose and answer questions about the natural world.  What do Biologists study?  Questions about how living.
{ Logic in Artificial Intelligence By Jeremy Wright Mathematical Logic April 10 th, 2012.
Artificial Intelligence Introductory Lecture Jennifer J. Burg Department of Mathematics and Computer Science.
UW Contributions: Past and Future Martin V. Butz Department of Cognitive Psychology University of Würzburg, Germany
Towards Cognitive Robotics Biointelligence Laboratory School of Computer Science and Engineering Seoul National University Christian.
Study on Genetic Network Programming (GNP) with Learning and Evolution Hirasawa laboratory, Artificial Intelligence section Information architecture field.
Psychology Liudexiang
제 6 주. 응용 -2: Graphics Artificial Life for Computer Graphics D. Terzopoulos, Communications of the ACM, vol. 42, no. 8, pp. 33~42, 1999 학습목표 Understanding.
Modeling Complex Dynamic Systems with StarLogo in the Supercomputing Challenge
Some Questions At what level(s) do we define an “organism”? Does it matter? How about systems in general? If it is true that there is a “universal law.
Artificial intelligence methods in the CO 2 permission market simulation Jarosław Stańczak *, Piotr Pałka **, Zbigniew Nahorski * * Systems Research Institute,
For the 4 th year students of Zoology P ractical A nimal B ehaviour  About this Course This course on animal behaviour provides a general introduction.
Evolving the goal priorities of autonomous agents Adam Campbell* Advisor: Dr. Annie S. Wu* Collaborator: Dr. Randall Shumaker** School of Electrical Engineering.
Neural Networks and Machine Learning Applications CSC 563 Prof. Mohamed Batouche Computer Science Department CCIS – King Saud University Riyadh, Saudi.
Hull University Business School Seminar, Hull, UK December 14, 2011 Dr. Viacheslav Maracha, Russia, Moscow Non-Profit Research Foundation "The Schedrovitsky.
Psychology and AI Author Yi Liu. What is intelligence Intelligence has been defined in many different ways, such as in terms of one’s capacity for logic,
KNOWLEDGE BASED SYSTEMS
CITS7212: Computational Intelligence An Overview of Core CI Technologies Lyndon While.
University of Kurdistan Artificial Intelligence Methods (AIM) Lecturer: Kaveh Mollazade, Ph.D. Department of Biosystems Engineering, Faculty of Agriculture,
Introduction to Artificial Intelligence CS 438 Spring 2008.
Lecture №1 Role of science in modern society. Role of science in modern society.
Comparative Reproduction Schemes for Evolving Gathering Collectives A.E. Eiben, G.S. Nitschke, M.C. Schut Computational Intelligence Group Department of.
Evolutionary Robotics The French Approach Jean-Arcady Meyer Commentator on the growth of the field. Animats: artificial animals anima-materials Coined.
Organic Evolution and Problem Solving Je-Gun Joung.
WHAT IS RESEARCH? According to Redman and Morry,
INTRODUCTION TO COGNITIVE SCIENCE NURSING INFORMATICS CHAPTER 3 1.
An Evolutionary Algorithm for Neural Network Learning using Direct Encoding Paul Batchis Department of Computer Science Rutgers University.
Evolving robot brains using vision Lisa Meeden Computer Science Department Swarthmore College.
What is cognitive psychology?
Scientific Research Group in Egypt (SRGE)
Chapter 11: Artificial Intelligence
Evolving the goal priorities of autonomous agents
Artificial Intelligence (CS 370D)
Sistem Kecerdasan Buatan
Evolution strategies Can programs learn?
CELLS SB1. Students will analyze the nature of the relationships between structures and functions in living CELLS. Explain the role of cell organelles.
Artificial Intelligence in an Agent-Based Model
Institute of Computing Technology
Introduction to Artificial Intelligence Instructor: Dr. Eduardo Urbina
Biology Overview The Study of Life What does the term Biology mean?
Presentation transcript:

Evolutionary Approach to Investigations of Cognitive Systems Vladimir Red ’ ko a), Anton Koval ’ b) a) Scientific Research Institute for System Analysis, Russian Academy of Science, Moscow b) National Nuclear Research University “ MEPhI ”, Moscow

Epistemological problem Epistemological problem: why human logical thinking is applicable to cognition of nature? To emphasize the problem, let us consider physics. The power of physics is due to effective use of mathematics. However, a mathematician makes logical inferences, proves theorems, basing on his mind, independently from physical world. Why are his results applicable to real nature, to real physical world? To investigate problem, it is reasonable to analyze cognitive evolution (evolution of animal cognitive abilities), evolutionary origin of human logical thinking. So, it is reasonable to model cognitive evolution

Sketch program: steps of modeling cognitive evolution (from simple animal cognitive abilities to mathematical deductions): 1)Modeling of adaptive behavior of autonomous agents that have natural needs: food, safety, reproduction 2)Investigation of the transition from the physical level of information processing in nervous system of animals to the level of the generalized “ notions ” 3)Investigations of processes of generating causal relations in animal memory 4)Investigations of “ logical conclusions ” in animal minds. Comparison of animal “ logic ” with human logic

Model of several needs and motivations (step 1 of the sketch program)

Several needs and motivations Population of autonomous agents is considered. Any agent has the following needs: food, safety, reproduction. Needs are characterized by motivations M F, M S, M R, and factors F F, F S, F R. Any time moment only one motivation is leading. Agent control system is set of rules S k  A k Rule weights W k are adjusted by means of both reinforcement learning and Darwinian evolution of agent population. Situation S k : 1) activity of the predator in vicinity of the agent, 2) previous action of the agent, 3) current leading motivation of the agent. Actions: 1) searching for food, 2) eating of food, 3) preparing for reproduction, 4) reproduction, 5) defence from a predator, 6) resting.

Several needs and motivations Scheme of choosing of leading motivation T F, T S, T R are thresholds M N is additional motivation (it becomes leading very rare) Changes of the factor (F F, F S or F R ) corresponding to the leading motivation are rewards at reinforcement learning

Several needs and motivations Results of computer simulations Dynamics of factors Dynamics of motivations Cycles of agent behavior and chains of actions are observed

Model of formation of generalized notions (step 2 of the sketch program)

Agent is searching for food in cellular environment Agent There are 10x10 cells. Portions of food are randomly distributed in 50 cells. Agent control system is set of rules: S k  A k, S k and A k are situation and action. Situation S k : presence or absence of food in agent field of vision. Actions A k : moving forward, turning left/right, eating, resting. Rule weights W k are adjusted by means of reinforcement learning Circles indicate agent field of vision. Arrow shows forward direction of agent

Formation of internal notions 1) food is here  “ eating ” ; 2) food is forward  “ moving forward ”, then “ eating ” ; 3,4) food is right/left  turning right/left, then “ moving forward ”, then “ eating ” ; 5) there is no food in field of vision  “ moving forward ” … 5 heuristics generalize selected rules: Internal notions of the agent are formed: 1) food is here, 2) food is forward, 3,4) food is right/left, 5) there is no food in field of vision

Adaptive behavior of modeled “ organisms ” Witkowski M. An action-selection calculus // Adaptive Behavior, V. 15. No. 1. PP Butz M.V., Sigaud O., Pezzulo G., Baldassarre G. (Eds.). Anticipatory Behavior in Adaptive Learning Systems: From Brains to Individual and Social Behavior. LNAI 4520, Berlin, Heidelberg: Springer Verlag, Vernon D., Metta G., Sandini G. A survey of artificial cognitive systems: Implications for the autonomous development of mental capabilities in computational agents // IEEE Transactions on Evolutionary Computation, special issue on Autonomous Mental Development, V. 11. No. 2. PP Intelligent autonomous agents

Sketch program: steps of modeling cognitive evolution 1)Modeling of adaptive behavior of autonomous agents that have natural needs: food, safety, reproduction 2)Investigation of the transition from the physical level of information processing in nervous system of animals to the level of the generalized “ notions ” 3)Investigations of processes of generating causal relations in animal memory 4)Investigations of “ logical conclusions ” in animal minds. Comparison of animal “ logic ” with human logic

Conclusion Comparing steps of the sketch program with our models and other works, it is possible to conclude that we can see some small fragments of a picture of cognitive evolution now, but we do not see the whole picture yet Nevertheless, investigations of cognitive evolution are interesting and important