2016-12-10

Neural Networks and Applications by S. Sengupta (IIT Kharagpur)

# click the upper-left icon to select videos from the playlist

source: nptelhrd    2009年9月22日
Electronics - Neural Networks and Applications by Prof. S. Sengupta, Department of Electronics and Electrical Communication Engineering, IIT Kharagpur.

Lec-1 Introduction to Artificial Neural Networks 53:50
Lec-2 Artificial Neuron Model and Linear Regression 58:28
Lec-3 Gradient Descent Algorithm 56:35
Lec-4 Nonlinear Activation Units and Learning Mechanisms 58:09
Lec-5 Learning Mechanisms-Hebbian,Competitive,Boltzmann 57:16
Lec-6 Associative memory 58:58
Lec-7 Associative Memory Model 57:16
Lec-8 Condition for Perfect Recall in Associative Memory 59:59
Lec-9 Statistical Aspects of Learning 54:08
Lec-10 V.C. Dimensions: Typical Examples 57:44
Lec-11 Importance of V.C. Dimensions Structural Risk Minimization 45:47
Lec-12 Single-Layer Perceptions 56:13
Lec-13 Unconstrained Optimization: Gauss-Newtons Method 59:17
Lec-14 Linear Least Squares Filters 57:58
Lec-15 Least Mean Squares Algorithm 52:21
Lec-16 Perceptron Convergence Theorem 55:29
Lec-17 Bayes Classifier & Perceptron: An Analogy 56:55
Lec-18 Bayes Classifier for Gaussian Distribution 55:51
Lec-19 Back Propagation Algorithm 55:35
Lec-20 Practical Consideration in Back Propagation Algorithm 57:09
Lec-21 Solution of Non-Linearly Separable Problems Using MLP 57:32
Lec-22 Heuristics For Back-Propagation 58:05
Lec-23 Multi-Class Classification Using Multi-layered Perceptrons 56:11
Lec-24 Radial Basis Function Networks: Cover's Theorem 56:49
Lec-25 Radial Basis Function Networks: Separability&Interpolation 57:24
Lec-26 Radial Basis Function as ill-Posed Surface Reconstruc 57:58
Lec-27 Solution of Regularization Equation: Greens Function 55:44
Lec-28 Use of Greens Function in Regularization Networks 57:14
Lec-29 Regularization Networks and Generalized RBF 48:47
Lec-30 Comparison Between MLP and RBF 54:09
Lec-31 Learning Mechanisms in RBF 54:37
Lec-32 Introduction to Principal Components and Analysis 56:38
Lec-33 Dimensionality reduction Using PCA 54:17
Lec-34 Hebbian-Based Principal Component Analysis 50:23
Lec-35 Introduction to Self Organizing Maps 39:05
Lec-36 Cooperative and Adaptive Processes in SOM 52:15
Lec-37 Vector-Quantization Using SOM 52:02