Evolution and Learning

Slides:



Advertisements
Similar presentations
Genetic Algorithms in Problem Solving EVOLVING COMPUTER PROGRAMS (1) t Evolving Lisp Programs Keplers Third Law: P 2 = cA 3 PROGRAM ORBITAL_PERIORD.
Advertisements

Department of Electronic Engineering NUIG Direct Evolution of Patterns using Genetic Algorithms By: John Brennan Supervisor: John Maher.
Department of Electronic Engineering NUIG Evolving Shapes using Direct & Indirect Encodings By: John Brennan Supervisor: John Maher.
1) What would happen to the population size if the average female produced more than one surviving reproducing daughter? A) there would be more females.
Slides from: Doug Gray, David Poole
Bio-Inspired Optimization. Our Journey – For the remainder of the course A brief review of classical optimization methods The basics of several stochastic.
1 Testing the Efficiency of Sensory Coding with Optimal Stimulus Ensembles C. K. Machens, T. Gollisch, O. Kolesnikova, and A.V.M. Herz Presented by Tomoki.
EvoNet Flying Circus Introduction to Evolutionary Computation Brought to you by (insert your name) The EvoNet Training Committee The EvoNet Flying Circus.
Genetic Algorithms Sushil J. Louis Evolutionary Computing Systems LAB Dept. of Computer Science University of Nevada, Reno
Reading population codes: a neural implementation of ideal observers Sophie Deneve, Peter Latham, and Alexandre Pouget.
ISSPIT Ajman University of Science & Technology, UAE
Parallelized Evolution System Onur Soysal, Erkin Bahçeci Erol Şahin Dept. of Computer Engineering Middle East Technical University.
EvoNet Flying Circus Introduction to Evolutionary Computation Brought to you by (insert your name) The EvoNet Training Committee The EvoNet Flying Circus.
T.J. Hartnett CSE 704 Seminar Dr. Miller Spring ‘11 EVOLVING CREATURES.
Genetic Algorithm for Variable Selection
2 What Genetic Programming ISN'T: What Genetic Programming ISN'T: Engineering a breed of purple carrots. Engineering a breed of purple carrots. Analyzing.
Reward processing (1) There exists plenty of evidence that midbrain dopamine systems encode errors in reward predictions (Schultz, Neuron, 2002) Changes.
Chapter 17: Evolution of Populations
Neural Optimization of Evolutionary Algorithm Strategy Parameters Hiral Patel.
Evolutionary Algorithms and Artificial Intelligence Paul Grouchy PhD Candidate University of Toronto Institute for Aerospace Studies
Genetic Algorithms and Ant Colony Optimisation
Experimental determination of motor model parameters ETEC6419.
Robotica Lezione 14. Lecture Outline  Neural networks  Classical conditioning  AHC with NNs  Genetic Algorithms  Classifier Systems  Fuzzy learning.
Evolving a Sigma-Pi Network as a Network Simulator by Justin Basilico.
C. Benatti, 3/15/2012, Slide 1 GA/ICA Workshop Carla Benatti 3/15/2012.
Soft Computing Lecture 18 Foundations of genetic algorithms (GA). Using of GA.
Reinforcement learning This is mostly taken from Dayan and Abbot ch. 9 Reinforcement learning is different than supervised learning in that there is no.
Lecture 8: 24/5/1435 Genetic Algorithms Lecturer/ Kawther Abas 363CS – Artificial Intelligence.
Computational Complexity Jang, HaYoung BioIntelligence Lab.
Neural and Evolutionary Computing - Lecture 9 1 Evolutionary Neural Networks Design  Motivation  Evolutionary training  Evolutionary design of the architecture.
Derivative Free Optimization G.Anuradha. Contents Genetic Algorithm Simulated Annealing Random search method Downhill simplex method.
1 Genetic Algorithms and Ant Colony Optimisation.
Evolving Virtual Creatures Karl Sims – SIGGRAPH ‘94 Presented by Andy Snyder.
Genetic Algorithms Przemyslaw Pawluk CSE 6111 Advanced Algorithm Design and Analysis
09/20/04 Introducing Proteins into Genetic Algorithms – CSIMTA'04 Introducing “Proteins” into Genetic Algorithms Virginie LEFORT, Carole KNIBBE, Guillaume.
Pac-Man AI using GA. Why Machine Learning in Video Games? Better player experience Agents can adapt to player Increased variety of agent behaviors Ever-changing.
Genetic Algorithms. The Basic Genetic Algorithm 1.[Start] Generate random population of n chromosomes (suitable solutions for the problem) 2.[Fitness]
Product Evolution: Computer-aided Recombinant Design by Customer-driven Natural Selection Kamal Malek Noubar Afeyan MIT Media Lab / The Center For Bits.
Franciszek Seredynski, Damian Kurdej Polish Academy of Sciences and Polish-Japanese Institute of Information Technology APPLYING LEARNING CLASSIFIER SYSTEMS.
CITS7212: Computational Intelligence An Overview of Core CI Technologies Lyndon While.
Optimizing with synapses Sebastian Seung Howard Hughes Medical Institute and Brain & Cog. Sci. Dept., MIT.
Introduction Genetic programming falls into the category of evolutionary algorithms. Genetic algorithms vs. genetic programming. Concept developed by John.
Evolutionary Robotics The Genotype-to-Phenotype Map The genotype to phenotype map: the algorithm that transforms the genotype into the phenotype. Direct.
Genetic Search Algorithms Matt Herbster. Why Another Search?  Designed in the 1950s, heavily implemented under John Holland (1970s)  Genetic search.
A field of study that encompasses computational techniques for performing tasks that require intelligence when performed by humans. Simulation of human.
Principles in the Evolutionary Design of Digital Circuits J. F. Miller, D. Job, and V. K. Vassilev Genetic Programming and Evolvable Machines.
Evolving Virtual Creatures B2.2 Vincent Visser | Complexity through simplicity.
Genes and Variation Genotypes and phenotypes in evolution Natural selection acts on phenotypes and does not directly on genes. Natural selection.
CAP6938 Neuroevolution and Artificial Embryogeny Real-time NEAT Dr. Kenneth Stanley February 22, 2006.
4/30/12. Explain what gene frequency is. Measure gene frequency in a model population. Make and test predictions about whether and how gene frequency.
Genetic Algorithm(GA)
Genetic Algorithms and Evolutionary Programming A Brief Overview.
I. Natural Selection Who Lives Who Dies.
Introduction Genetic programming falls into the category of evolutionary algorithms. Genetic algorithms vs. genetic programming. Concept developed by John.
What is this “Viterbi Decoding”
A Distributed Genetic Algorithm for Learning Evaluation Parameters in a Strategy Game Gary Matthias.
Evolution Notes March
Genetic Algorithm and Their Applications to Scheduling
Process modelling and optimization aid
إستراتيجيات ونماذج التقويم
Evolution of Populations: Part I
Homework Schultz, Dayan, & Montague, Science, 1997
The Evolution of Learning Algorithms for Artificial Neural Networks
IV. Convolutional Codes
A Tutorial Keith A. Woodbury Mechanical Engineering Department
The role of Genetics and DNA in Evolution (Ch 16.1)
B6 Genetics- Paper2 Revision
B6 Genetics- Paper2 Revision
Population Based Metaheuristics
IV. Convolutional Codes
Presentation transcript:

Evolution and Learning Braitenberg 6: Selection, the Impersonal Engineer Braitenberg 7: Concepts EXAMPLES: Modeling evolution: genetic algorithms Modeling learning: reinforcement learning (bee foraging)

Genetic Algorithms genetic coding (chromosome/genes) genotype  phenotype (development) evaluation, of individuals in a population selection, based on fitness variation, genetic modification of selected repeat

sensorL sensorR Parameters to encode: Input gains: 2 Time constants: 2 Thresholds: 4 Injection current: 4 Injection noise: 4 Synaptic weights: 4 Syn. time constants: 4 Output gains: 2 TOTAL: 26 Assume 4 bit resolution per parameter (16 possible values): 26 * 4 = 104 bits 2104 possibilities !!! motorL motorR

Learning vs. evolution

Functional organization (bee brain)

Reinforcement Learning Montague PR, Dayan P, Person C, Sejnowski TJ (1995) Bee foraging in uncertain environments using predictive Hebbian learning. Nature 377, 725 - 728 S R P N B r(t) Sensory Input Nectar Action δ(t) WB WN WY Y Diagram from: http://www.cs.stir.ac.uk/~kjt/teaching/31z7/posters/2003/igb.ppt