Learn · Neural Networks for Signal Processing - I
Lecture 2 of 66Week 1 - Introduction to Neural Networks
Introduction to Neural Networks
Prof. Shayan Srinivasa Garani · IISc Bangalore
Credits and licence
- From
- Neural Networks for Signal Processing - I, IISc Bangalore (at NPTEL)
- Licence
- CC BY-NC-SA, as NPTEL states it. Non-commercial use only.
- Attribution
- NPTEL states: "Distributed under Creative Commons Attribution-ShareAlike / CC BY - NC - SA", beside a BY-NC-SA badge.
- Who can watch
- Tweens profiles and older. How courses are placed
All the lectures
- The Human Brain
- Introduction to Neural Networks
- Models of a neuron
- Feedback and network architectures
- Knowledge representation
- Prior information and invariances
- Learning processes
- Perceptron 1
- Perceptron 2
- Batch perceptron algorithm
- Perceptron and Bayes classifier
- Linear regression 1
- Linear regression 2
- Linear regression 3
- Logistic regression
- Multi-layer perceptron 1
- Multi-layer perceptron 2
- Back propagation 1
- Back propagation 2
- XOR problem
- Universal approximation theorem
- Complexity Regularization and Cross validation
- Convolutional Neural Networks (CNN)
- Cover’s Theorem
- Multivariate interpolation problem
- Radial basis functions (RBF)
- Recursive least squares algorithm
- Comparison of RBF with MLP
- Kernel regression using RBFs
- Kernel Functions
- Basics of constrained optimization
- Optimization with equality constraint
- Optimization with inequality constraint
- Support Vector Machines (SVM)
- Optimal hyperplane for linearly separable patterns
- Quadratic optimization for finding optimal hyperplane
- Optimal hyperplane for non-linearly separable patterns
- Inner product kernel and Mercer’s theorem
- Optimal design of an SVM
- ε-insensitive loss function
- XOR problem revisited using SVMs
- Hilbert Space
- Reproducing Kernel Hilbert Space
- Representer Theorem
- Generalized applicability of the representer theorem
- Regularization Theory
- Euler-Lagrange Equation
- Regularization Networks
- Generalized RBF networks
- XOR problem revisited using RBF
- Structural Risk Minimization
- Bias-Variance Dilemma
- Estimation of regularization parameters
- Basics of L1 regularization
- Grafting
- VC dimension
- Autoencoders
- Denoising Autoencoders
- Kernel PCA
- Hebbian based maximum eigen filter -1
- Hebbian based maximum eigen filter -2
- Hebbian based maximum eigen filter - 3
- Demo – Perceptron
- Demo – Motivation for CNN
- Back propagation in Convolutional Neural Network
- Ethics in AI research and coverage summary