Course Syllabus:
Artificial Neuron, Neuronal Network and Regression
- McCulloch–Pitts Neuron model
- Network Architecture, Design and Learning
- Linear regression
Unconstrained Optimization and LMS
- Unconstrained Optimization
- LMS algorithm and its structure
Perceptron and Activation
- Rosenblatt’s Perceptron
- Perceptron Convergence Algorithm
- Batch Perceptron Algorithm
- Activation functions
Multilayer Perceptron and Back Propagation
- Architecture, Batch and Online Learning
- Back Propagation Algorithm and its Attributes
- Back Propagation Heuristics & More
DNN: Convolutional Neural Networks
- CNN computations
- Training the CNN & Architectures
DNN: Generative Adversarial Networks (GAN)
- Motivation and Construction of GAN
- Deep Convolutional GAN
- GAN variants: Conditional GAN, Wasserstein GAN, Cycle GAN, PatchGAN, InfoGAN, BiGAN, RealnessGAN
Other DNNs: Recurrent Neural Networks and Auto Encoders
- Long Short Term Memory (LSTM) Network
- Classical, Adversarial and Variational Deep Auto Encoders
DNN Theory:
- Why Deep Nets work better?
DNN Coding: [Led by the TAs]
- Intro to Google CoLab, Pytorch
- CNN, LSTM, AE and GAN coding
Online Lecture Management:
- Google Classroom [invitation based, exclusive to those who officially register]