Neural Networks and Applications [2021]

Course Syllabus:

Artificial Neuron, Neuronal Network and Regression

- McCulloch–Pitts Neuron model

- Network Architecture, Design and Learning

- Linear regression

Unconstrained Optimization and Least Mean Square (LMS)

- Unconstrained Optimization

- LMS algorithm and its structure

Perceptron

- Rosenblatt’s Perceptron

- Perceptron Convergence Algorithm

- Bayes Classification & Logistic Regression

- Batch Perceptron Algorithm

Multilayer Perceptron and Back Propagation

- Basic Architecture, Batch and Online Learning

- Back Propagation Algorithm and its Attributes

- Back Propagation Heuristics & More

Convolutional Neural Networks (CNN)

- CNN computations

- Training the CNN (hyperparameter & optimization choices)

- CNN architectures

Generative Adversarial Networks (GAN)

- Construction of GAN, Deep Convolutional GAN

- GAN variants: Conditional GAN, Wasserstein GAN, Cycle GAN, PatchGAN, InfoGAN, BiGAN, RealnessGAN

Recurrent Neural Networks (RNN), Transformers, Auto Encoders & GNN

- RNN, Bidirectional RNN, Long Short Term Memory (LSTM) Network

- Transformer & Attention networks

- Classical, Adversarial and Variational Deep Auto Encoders

- Contrastive & Competitive Learning

- Introduction to Graph Neural Network (GNN)

Coding tutorials & hands-on: [in parallel, 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]