Neural Networks and Applications. Instructor: Prof. Somnath Sengupta, Department of Electronics and Electrical Communication Engineering, IIT Kharagpur.

FREE
This course includes
Hours of videos

1027 years, 8 months

Units & Quizzes

37

Unlimited Lifetime access
Access on mobile app
Certificate of Completion

This course covers lessons in artificial neural networks, associative memory, single layer perceptrons, back propagation algorithm, learning mechanisms in Radial Basis Function (RBF) and vector-quantization using Self-Organizing Maps (SOM). (from nptel.ac.in)

Course Currilcum

  • Lecture 01 – Introduction to Artificial Neural Networks Unlimited
  • Lecture 02 – Artificial Neural Model and Linear Regression Unlimited
  • Lecture 03 – Gradient Descent Algorithm Unlimited
  • Lecture 04 – Nonlinear Activation Units and Learning Mechanisms Unlimited
  • Lecture 05 – Learning Mechanisms – Hebbian, Competitive, Boltzmann Unlimited
  • Lecture 06 – Associative Memory Unlimited
  • Lecture 07 – Associative Memory Model Unlimited
  • Lecture 08 – Condition for Perfect Recall in Associative Memory Unlimited
  • Lecture 09 – Statistical Aspects of Learning Unlimited
  • Lecture 10 – VC Dimensions: Typical Examples Unlimited
  • Lecture 11 – Importance of VC Dimensions: Structural Risk Minimization Unlimited
  • Lecture 12 – Single Layer Perceptions Unlimited
  • Lecture 13 – Unconstrained Optimization: Gauss-Newton’s Method Unlimited
  • Lecture 14 – Linear Least Square Filters Unlimited
  • Lecture 15 – Least Mean Squares Algorithm Unlimited
  • Lecture 16 – Perceptron Convergence Theorem Unlimited
  • Lecture 17 – Bayes Classifier and Perceptron: An Analogy Unlimited
  • Lecture 18 – Bayes Classifier for Gaussian Distribution Unlimited
  • Lecture 19 – Backpropagation Algorithm Unlimited
  • Lecture 20 – Practical Consideration in Backpropagation Algorithm Unlimited
  • Lecture 21 – Solution of Nonlinearly Separable Problems using Multilayer Perceptron (MLP) Unlimited
  • Lecture 22 – Heuristics for Backpropagation Unlimited
  • Lecture 23 – Multiclass Classification using Multilayered Perceptrons Unlimited
  • Lecture 24 – Radial Basis Function Networks: Cover’s Theorem Unlimited
  • Lecture 25 – Radial Basis Function Networks: Separability and Interpolation Unlimited
  • Lecture 26 – Radial Basis Function as Ill-Posed Surface Reconstruction Unlimited
  • Lecture 27 – Solution of Regularization Equation: Green’s Function Unlimited
  • Lecture 28 – Use of Green’s Function in Regularization Networks Unlimited
  • Lecture 29 – Regularization Networks and Generalized Radial Basis Function (RBF) Unlimited
  • Lecture 30 – Comparison between MLP and RBF Unlimited
  • Lecture 31 – Learning Mechanisms in Radial Basis Function (RBF) Unlimited
  • Lecture 32 – Introduction to Principal Components and Analysis Unlimited
  • Lecture 33 – Dimensionality Reduction using Principal Components Analysis (PCA) Unlimited
  • Lecture 34 – Hebbian-Based Principal Components Analysis Unlimited
  • Lecture 35 – Introduction to Self-Organizing Maps Unlimited
  • Lecture 36 – Cooperative and Adaptive Processes in Self-Organizing Maps (SOM) Unlimited
  • Lecture 37 – Vector-Quantization using Self-Organizing Maps (SOM) Unlimited