infocobuild

Neural Networks and Applications

Neural Networks and Applications. Instructor: Prof. Somnath Sengupta, Department of Electronics and Electrical Communication Engineering, IIT Kharagpur. This course covers lessons in artificial neural networks, associative memory, single layer perceptrons, back propagation algorithm, learning mechanisms in Radial Basis Function (RBF) and vector-quantization using Self-Organizing Maps (SOM). (from nptel.ac.in)

Introduction


Lecture 01 - Introduction to Artificial Neural Networks
Lecture 02 - Artificial Neural Model and Linear Regression
Lecture 03 - Gradient Descent Algorithm
Lecture 04 - Nonlinear Activation Units and Learning Mechanisms
Lecture 05 - Learning Mechanisms - Hebbian, Competitive, Boltzmann
Lecture 06 - Associative Memory
Lecture 07 - Associative Memory Model
Lecture 08 - Condition for Perfect Recall in Associative Memory
Lecture 09 - Statistical Aspects of Learning
Lecture 10 - VC Dimensions: Typical Examples
Lecture 11 - Importance of VC Dimensions: Structural Risk Minimization
Lecture 12 - Single Layer Perceptions
Lecture 13 - Unconstrained Optimization: Gauss-Newton's Method
Lecture 14 - Linear Least Square Filters
Lecture 15 - Least Mean Squares Algorithm
Lecture 16 - Perceptron Convergence Theorem
Lecture 17 - Bayes Classifier and Perceptron: An Analogy
Lecture 18 - Bayes Classifier for Gaussian Distribution
Lecture 19 - Backpropagation Algorithm
Lecture 20 - Practical Consideration in Backpropagation Algorithm
Lecture 21 - Solution of Nonlinearly Separable Problems using Multilayer Perceptron (MLP)
Lecture 22 - Heuristics for Backpropagation
Lecture 23 - Multiclass Classification using Multilayered Perceptrons
Lecture 24 - Radial Basis Function Networks: Cover's Theorem
Lecture 25 - Radial Basis Function Networks: Separability and Interpolation
Lecture 26 - Radial Basis Function as Ill-Posed Surface Reconstruction
Lecture 27 - Solution of Regularization Equation: Green's Function
Lecture 28 - Use of Green's Function in Regularization Networks
Lecture 29 - Regularization Networks and Generalized Radial Basis Function (RBF)
Lecture 30 - Comparison between MLP and RBF
Lecture 31 - Learning Mechanisms in Radial Basis Function (RBF)
Lecture 32 - Introduction to Principal Components and Analysis
Lecture 33 - Dimensionality Reduction using Principal Components Analysis (PCA)
Lecture 34 - Hebbian-Based Principal Components Analysis
Lecture 35 - Introduction to Self-Organizing Maps
Lecture 36 - Cooperative and Adaptive Processes in Self-Organizing Maps (SOM)
Lecture 37 - Vector-Quantization using Self-Organizing Maps (SOM)

References
Neural Networks and Applications
Instructor: Prof. Somnath Sengupta, Department of Electronics and Electrical Communication Engineering, IIT Kharagpur. This course covers lessons in artificial neural networks.