Lec-1 Introduction to Artificial Neural Networks
Lec-2 Artificial Neuron Model and Linear Regression
Lec-3 Gradient Descent Algorithm
Lec-4 Nonlinear Activation Units and Learning Mechanisms
Lec-5 Learning Mechanisms-Hebbian,Competitive,Boltzmann
Lec-6 Associative memory
Lec-7 Associative Memory Model
Lec-8 Condition for Perfect Recall in Associative Memory
Lec-9 Statistical Aspects of Learning
Lec-10 V.C. Dimensions: Typical Examples
Lec-11 Importance of V.C. Dimensions Structural Risk Minimization
Lec-12 Single-Layer Perceptions
Lec-13 Unconstrained Optimization: Gauss-Newtons Method
Lec-14 Linear Least Squares Filters
Lec-15 Least Mean Squares Algorithm
Lec-16 Perceptron Convergence Theorem
Lec-17 Bayes Classifier&Perceptron: An Analogy lecture
Lec-18 Bayes Classifier for Gaussian Distribution lecture
Lec-19 Back Propagation Algorithm
Lec-20 Practical Consideration in Back Propagation Algorithm
Lec-21 Solution of Non-Linearly Separable Problems Using MLP
Lec-22 Heuristics For Back-Propagation
Lec-23 Multi-Class Classification Using Multi-layered Perceptrons
Lec-24 Radial Basis Function Networks: Covers Theorem
Lec-25 Radial Basis Function Networks: Separability&Interpolation
Lec-26 Radial Basis Function as ill-Posed Surface Reconstruc
Lec-27 Solution of Regularization Equation: Greens Function
Lec-28 Use of Greens Function in Regularization Networks
Lec-29 Regularization Networks and Generalized RBF
Lec-30 Comparison Between MLP and RBF
Lec-31 Learning Mechanisms in RBF
Lec-32 Introduction to Principal Components and Analysis
Lec-33 Dimensionality reduction Using PCA
Lec-34 Hebbian-Based Principal Component Analysis
Lec-35 Introduction to Self Organizing Maps
Lec-36 Cooperative and Adaptive Processes in SOM
Lec-37 Vector-Quantization Using SOM