Scribd
Upload
36 views

ANN Deep Learning Course Structure AUG-DEC2023

This 12-class course covers the basics of neural networks and deep learning including backpropagation algorithms, regularization techniques, convolutional and recurrent neural networks, and deep generative models like GANs. The course will also cover deep learning frameworks and accelerating neural network performance using GPUs. Prerequisites include basics of probability, statistics, linear algebra, and optimization theory. References include the book Deep Learning by Goodfellow et al. and Neural Network Design by Hagan et al.

Uploaded by

blend.saketkumar
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
36 views

ANN Deep Learning Course Structure AUG-DEC2023

This 12-class course covers the basics of neural networks and deep learning including backpropagation algorithms, regularization techniques, convolutional and recurrent neural networks, and deep generative models like GANs. The course will also cover deep learning frameworks and accelerating neural network performance using GPUs. Prerequisites include basics of probability, statistics, linear algebra, and optimization theory. References include the book Deep Learning by Goodfellow et al. and Neural Network Design by Hagan et al.

Uploaded by

blend.saketkumar
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

MG225 : Decision Models - Neural Networks and Deep Learning Aug-Dec, 2023

Dr. Amritendu Mukherjee*


Prof. Parthasarathy Ramachandran„
Prerequisites : Basics of Probability and Statistics, Linear Algebra and Optimization Theory.

Course Structure :

Class I : Basics of Artificial Neural Networks (ANN)


Introduction to Machine Learning (ML); Discussions on different ML methodologies; Influence of Biological
Nervous System on development of ANN; Basic Perceptron structure; Perceptron learning rule; Different types
of Activation functions; Input/Output relationship and estimation of Weights.

Class II & III : Gradient Descent and Backpropagation Algorithms:


Discussion on Gradient Descent algorithm & parameter optimization with gradient descent; Stochastic Gradient
Descent (SGD); Basic Backpropagation algorithm; Different variations of Backpropagation algorithms -
Levenberg-Marquardt(LM), Bayesian Regularization(BR), Resilient Backpropagation(Rprop) etc.

Class IV & V : Parameter Regularization, Input Normalization and Weight Initialization:


Bias-Variance Trade Off, Tuning neural networks to improve generalization performance, Regularization to
avoid overfitting, Various methods for weight initialization - Zero, Random, Xavier, He etc.

Class VI & VII : Deep Neural Networks:


Difference Between Machine Learning and Deep Learning; Introduction to Deep Neural Networks -
Convolutional Neural Network (CNN) & Recurrent Neural Network (RNN)

Class VIII & IX : Examples of Advanced DNN Architectures


Image Classification - AlexNet, VGG-16, ResNet-50 etc.; Image Segmentation - U-Net, U-Net++, ResUNet++
etc.; Long Short-Term Memory (LSTM) Networks; Bidirectional LSTMs; Transformer Architecture

Class X & XI : Deep Generative Models:


Gaussian Mixture Model - GMM; Autoencoders (AE) & Variational Autoencoders (VAE); Variational
Divergence Minimization (VDM) & Generative Adversarial Network (GAN); Score-Based Generative Models

Class XII : Implementation of Deep Neural Networks


Accelerating performances of DNN Architecture using GPUs and other H/W Platforms [HPU, IPU etc.] along
with Software Libraries; Various Deep Learning Frameworks [TensorFlow, PyTorch, JAX etc.]

References :
ˆ Deep Learning by Ian Goodfellow, Yoshua Bengio & Aaron Courville (http://www.deeplearningbook.org/)
ˆ Neural Network Design by Martin T. Hagan, Howard B. Demuth, Mark Hudson Beale & Orlando De Jesús
Link : https://hagan.okstate.edu/NNDesign.pdf

Note: Papers, GitHub repositories and other materials associated to the particular lecture would be shared at
the time of conducting the session for the same.

* CTO & Co-Founder - NeuroPixel.AI Labs; [email protected], [email protected]


„ Professor, Department Of Management Studies, Indian Institute of Science, Bangalore; [email protected]

You might also like