IISc Bangalore · Engineering

Neural Networks for Signal Processing – I

Prof. Shayan Srinivasa Garani · 2018 · 66 free video lectures

This will be an introductory graduate level course in neural networks for signal processing. The course starts with a motivation of how the human brain is inspirational to building artificial neural networks. The neural networks are viewed as directed graphs with various network topologies towards…

▶ Play on Open Lecture HallCourse page ↗

Lectures

  1. The Human Brain
  2. Introduction to Neural Networks
  3. Models of a neuron
  4. Feedback and network architectures
  5. Knowledge representation
  6. Prior information and invariances
  7. Learning processes
  8. Perceptron 1
  9. Perceptron 2
  10. Batch perceptron algorithm
  11. Perceptron and Bayes classifier
  12. Linear regression 1
  13. Linear regression 2
  14. Linear regression 3
  15. Logistic regression
  16. Multi-layer perceptron 1
  17. Multi-layer perceptron 2
  18. Back propagation 1
  19. Back propagation 2
  20. XOR problem
  21. Universal approximation theorem
  22. Complexity Regularization and Cross validation
  23. Convolutional Neural Networks (CNN)
  24. Cover’s Theorem
  25. Multivariate interpolation problem
  26. Radial basis functions (RBF)
  27. Recursive least squares algorithm
  28. Comparison of RBF with MLP
  29. Kernel regression using RBFs
  30. Kernel Functions
  31. Basics of constrained optimization
  32. Optimization with equality constraint
  33. Optimization with inequality constraint
  34. Support Vector Machines (SVM)
  35. Optimal hyperplane for linearly separable patterns
  36. Quadratic optimization for finding optimal hyperplane
  37. Optimal hyperplane for non-linearly separable patterns
  38. Inner product kernel and Mercer’s theorem
  39. Optimal design of an SVM
  40. ε-insensitive loss function
  41. XOR problem revisited using SVMs
  42. Hilbert Space
  43. Reproducing Kernel Hilbert Space
  44. Representer Theorem
  45. Generalized applicability of the representer theorem
  46. Regularization Theory
  47. Euler-Lagrange Equation
  48. Regularization Networks
  49. Generalized RBF networks
  50. XOR problem revisited using RBF
  51. Structural Risk Minimization
  52. Bias-Variance Dilemma
  53. Estimation of regularization parameters
  54. Basics of L1 regularization
  55. Grafting
  56. VC dimension
  57. Autoencoders
  58. Denoising Autoencoders
  59. Kernel PCA
  60. Hebbian based maximum eigen filter -1
  61. Hebbian based maximum eigen filter -2
  62. Hebbian based maximum eigen filter - 3
  63. Demo – Perceptron
  64. Demo – Motivation for CNN
  65. Back propagation in Convolutional Neural Network
  66. Ethics in AI research and coverage summary

From NPTEL (IITs and IISc) · CC BY-NC-SA. More from IISc Bangalore.

Open Lecture Hall is free, with no ads and no sign-up. It is not run by or connected to any university; the lectures are the universities' own free recordings, played from where they host them. About & rights