BIOLOGICAL BASICS AND HISTORICAL CONTEXT OF NEURAL COMPUTATION - neurones, synapses, action potential, circuits, brain, neural computation and computational neuroscience - associationism, instructivism, Hebb's rule, the McCulloch-Pitts Neuron, the rise of cybernetics and GST, Macey Conferences, Perceptron and non linear sepearbility, dynamical systems, emergent computation, etc (3 Lectures) THE MULTILAYERED PERCEPTRON - contrast with Perceptron. Representation. Feedforward and feedback phases. Sigmoidal functions, activation, generalised delta rule, adaptation and learning, convergence, gradient descent, recent developments (3 Lectures) KOHONEN SELF ORGANISING MAPS - nature of unsupervised learning, clustering and comparisons with statistical methods such as k-means and PCA, Iris data set, competitive learning, the learning algorithm (3 Lectures) THE INTERPRETATION PROBLEM - nature and issues related to problems using ANNs i
ncluding symbol grounding, bootstrap, representation. Issues in practice (3 Lectures) BIOLOGICALLY-INSPIRED DESIGNS AND COMPUTATIONAL NEUROSCIENCES - resumé based on Shepherd, Koch et al (3 Lectures) INTRODUCTION TO EVOLUTIONARY COMPUTATION - historical review, describing the selectionist paradigm (3 Lectures) BIOLOGICAL MOTIVATION - basic genetics, population dynamics and "fitness" (3 Lectures) THE BASIC STRUCTURE OF THE GENETIC ALGORITHM (3 Lectures) CASE STUDIES OF APPLICATIONS OF GENETIC ALGORITHMS (3 Lectures) WHY DO GENETIC ALGORITHMS WORK? - The Schema Theorem ("Building Block Hypothesis") (2 Lectures) OTHER EVOLUTIONARY METHODS - Genetic Programming, Classifier Systems, Evolutionary Strategies (1 Lecture)
|