AD-601 Deep Learning Notes
5 notes for Deep Learning, unit by unit.
Notes for AD-601
- Unit 1 · Short notes Introduction to Deep Learning Biological Neuron · Idea of computational units · McCulloch–Pitts Neural Model · Linear Perceptron · Perceptron Learning · Feed Forward and Back Propagation Networks
- Unit 2 · Short notes Feedforward Networks Multilayer Perceptron · Gradient Descent · Backpropagation · Empirical Risk Minimization · Regularization · Autoencoders
- Unit 3 · Short notes Convolutional Networks Convolution Operation · Variants of the Basic Convolution Function · Structured Outputs · Efficient Convolution Algorithms · Random or Unsupervised Features · LeNet
- Unit 4 · Short notes Recurrent Neural Networks Bidirectional RNNs · Deep Recurrent Networks · Recursive Neural Networks · Long Short-Term Memory (LSTM) · Other Gated RNNs
- Unit 5 · Short notes Deep Generative Models Boltzmann Machines · Restricted Boltzmann Machines · MCMC and Gibbs Sampling · Gradient Computations in RBMs · Deep Belief Networks · Deep Boltzmann Machines
More for AD-601
Other 6th semester AD subjects
- AD-602 Computer Networks
- AD-603 (A) Data Mining and Warehousing
- AD-603 (B) Digital Image Processing
- AD-603 (C) Information Retrieval
- AD-604 (A) Internet of Things
- AD-604 (B) Block Chain Technologies
- AD-604 (C) Compiler Design