Curso de Redes Neurais Artificiais (Artificial Neural Networks) do Centre for Educational Technology - Indian Institute of Technology - Kharagpur
Abaixo vão os links para as vídeo-aulas:
1 - Introduction to Artificial Neural Networks
2 - Artificial Neuron Model and Linear Regression
3 - Gradient Descent Algorithm
4 - Nonlinear Activation Units and Learning Mechanisms
5 - Learning Mechanisms-Hebbian,Competitive,Boltzmann
8 - Condition for Perfect Recall in Associative Memory
9 - Statistical Aspects of Learning
10 - V.C. Dimensions: Typical Examples
11 - Importance of V.C. Dimensions Structural Risk Minimization
13 - Unconstrained Optimization: Gauss-Newton's Method
14 - Linear Least Squares Filters
15 - Least Mean Squares Algorithm
16 - Perceptron Convergence Theorem
17 - Bayes Classifier & Perceptron: An Analogy
18 - Bayes Classifier for Gaussian Distribution
19 - Back Propagation Algorithm
20 - Practical Consideration in Back Propagation Algorithm
21 - Solution of Non-Linearly Separable Problems Using MLP
22 - Heuristics For Back-Propagation
23 - Multi-Class Classification Using Multi-layered Perceptrons
24 - Radial Basis Function Networks: Cover's Theorem
25 - Radial Basis Function Networks: Separability & Interpolation
26 - Radial Basis Function as ill-Posed Surface Reconstruction
27 - Solution of Regularization Equation: Greens Function
28 - Use of Greens Function in Regularization Networks
29 - Regularization Networks and Generalized RBF
30 - Comparison Between MLP and RBF
31 - Learning Mechanisms in RBF
32 - Introduction to Principal Components and Analysis
33 - Dimensionality reduction Using PCA
34 - Hebbian-Based Principal Component Analysis
35 - Introduction to Self Organizing Maps
