» MIT OpenCourseWare » Brain and Cognitive Sciences » Introduction to Neural Networks, Fall 2002

Calendar

The optional recitations are designed to teach students the basics of MATLAB® and the special functions that are required to complete the problem sets.


	LEC #				TOPICS


	Lecture 1				Definitions of Computational Neuroscience and Neural Networks. Classical Neural Network Equations. Integrate-and-Fire Model Neurons and Reduction by the Method of Averaging


	Optional Recitation 1				Discuss Homework 1. Review of Basic Differential Equations, Taylor Approximations, and MATLAB^®. Skills for Homework 1


	Lecture 2				Perceptron as Feature Detector. Visual Receptive Fields Assignment 1: Integrate-and-fire Neurons, Method of Averaging


	Lecture 3				The Problem of Credit Assignment. Perceptron Learning Rule. Convergence Theorem. Learning by Gradient Following. Online Learning


	Optional Recitation 2				Homework 2. Manipulating the MNIST Database in MATLAB^®. Eigenvalues. Plotting Contours in MATLAB^®


	Lecture 4				Multilayer Perceptrons and Backpropagation Assignment 2: Perceptrons


	Lecture 5				Backpropagation Applications. LeNet and the Visual System


	Lecture 6				The Capacity of the Perceptron, Statistical Learning Theory Assignment 3. Backpropagation


	Lecture 7				Unsupervised Learning for Perceptrons. Mean and Principal Component


	Lecture 8				Feedback in Linear Networks. Eigenmode Analysis, Amplification and Attenuation, Gain-bandwidth Theorem


	Lecture 9				Neural Network models of the Retina


	Lecture 10				Self-excitation and Global Inhibition. Decision-making. The MAX Operation Assignment 5: Linear Network Theory


	Lecture 11				Hybrid Analog-digital Computation. Permitted and Forbidden Sets


					Midterm Review


					Midterm Exam


	Lecture 12				Intra-group Excitation and Global Inhibition. Marr-Poggio Model of Stereopsis. Complex Cell Model Assignment 6: Nonlinear Network Theory


	Lecture 13				Lateral Excitation and Global Inhibition. Gain Fields and Stimulus Selection


	Lecture 14				Rehash of Midterm Exam


	Lecture 15				Vector Quantization (VQ) Principal Component Analysis (PCA) Assignment 7: Nonlinear Network Theory Again


	Lecture 16				Models of Associative Memory


	Lecture 17				Delay Sctivity. Griniasty-Tsodyks-Amit Model Assignment 8: VQ


	Lecture 18				Neural Integrators


	Lecture 19				Contrastive Hebbian Learning and Recurrent Backprop Learning Assignment 9 due


	Lecture 20				Reinforcement Learning. Hedonistic Synapses


	Lecture 21				REINFORCE Algorithms. Hedonistic Neurons Assignment 10 Due


	Lecture 22				Gradient Learning of Trajectories: Backpropagation and Real-time Recurrent Learning


	Lecture 23				Assignment 11 Due


	Lecture 24				Final Review


					Final Exam Review Session

MATLAB^® is a trademark of The MathWorks, Inc.

Search

Calendar