NOC:Neural Networks for Signal Processing-I


Lecture 1 - The human brain


Lecture 2 - Introduction to Neural Networks


Lecture 3 - Models of a neuron


Lecture 4 - Feedback and network architectures


Lecture 5 - Knowledge representation


Lecture 6 - Prior information and invariances


Lecture 7 - Learning processes


Lecture 8 - Perceptron - 1


Lecture 9 - Perceptron - 2


Lecture 10 - Batch perceptron algorithm


Lecture 11 - Perceptron and Bayes classifier


Lecture 12 - Linear regression - 1


Lecture 13 - Linear regression - 2


Lecture 14 - Linear regression - 3


Lecture 15 - Logistic regression


Lecture 16 - Multi-layer perceptron - 1


Lecture 17 - Multi-layer perceptron - 2


Lecture 18 - Back propagation - 1


Lecture 19 - Back propagation - 2


Lecture 20 - XOR problem


Lecture 21 - Universal approximation function


Lecture 22 - Complexity Regularization and Cross validation


Lecture 23 - Convolutional Neural Networks (CNN)


Lecture 24 - Cover’s Theorem


Lecture 25 - Multivariate interpolation problem


Lecture 26 - Radial basis functions (RBF)


Lecture 27 - Recursive least squares algorithm


Lecture 28 - Comparison of RBF with MLP


Lecture 29 - Kernel regression using RBFs


Lecture 30 - Kernel Functions


Lecture 31 - Basics of constrained optimization


Lecture 32 - Optimization with equality constraint


Lecture 33 - Optimization with inequality constraint


Lecture 34 - Support Vector Machines (SVM)


Lecture 35 - Optimal hyperplane for linearly separable patterns


Lecture 36 - Quadratic optimization for finding optimal hyperplane


Lecture 37 - Optimal hyperplane for non-linearly separable patterns


Lecture 38 - Inner product kernel and Mercer’s theorem


Lecture 39 - Optimal design of an SVM


Lecture 40 - ε-insensitive loss function


Lecture 41 - XOR problem revisited using SVMs


Lecture 42 - Hilbert Space


Lecture 43 - Reproducing Kernel Hilbert Space


Lecture 44 - Representer Theorem


Lecture 45 - Generalized applicability of the representer theorem


Lecture 46 - Regularization Theory


Lecture 47 - Euler-Lagrange Equation


Lecture 48 - Regularization Networks


Lecture 49 - Generalized RBF networks


Lecture 50 - XOR problem revisited using RBF


Lecture 51 - Structural Risk Minimization


Lecture 52 - Bias-Variance Dilemma


Lecture 53 - Estimation of regularization parameters


Lecture 54 - Basics of L1 regularization


Lecture 55 - Grafting


Lecture 56 - Kernel PCA


Lecture 57 - Hebbian based maximum eigen filter - 1


Lecture 58 - Hebbian based maximum eigen filter - 2


Lecture 59 - Hebbian based maximum eigen filter - 3


Lecture 60 - VC dimension


Lecture 61 - Autoencoders


Lecture 62 - Denoising Autoencoders


Lecture 63 - Demo - Perceptron


Lecture 64 - Demo - Motivation for CNN


Lecture 65 - Back propagation in Convolutional Neural Network


Lecture 66 - Ethics in AI research and coverage summary