Scribd
Upload
4 views

deepLearning

The INT422 Deep Learning course focuses on building and optimizing deep learning models using TensorFlow and Keras, covering topics such as convolutional neural networks, autoencoders, recurrent neural networks, and generative adversarial networks. Students will engage in practical experiments, including data preprocessing, model training, and performance evaluation. The course aims to equip students with the skills to apply deep learning techniques to real-world problems.

Uploaded by

suryanshyadav885
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
4 views

deepLearning

The INT422 Deep Learning course focuses on building and optimizing deep learning models using TensorFlow and Keras, covering topics such as convolutional neural networks, autoencoders, recurrent neural networks, and generative adversarial networks. Students will engage in practical experiments, including data preprocessing, model training, and performance evaluation. The course aims to equip students with the skills to apply deep learning techniques to real-world problems.

Uploaded by

suryanshyadav885
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

INT422:DEEP LEARNING

L:2 T:0 P:2 Credits:3

Course Outcomes: Through this course students should be able to

CO1 :: understand TensorFlow to build and optimize deep learning models

CO2 :: define the hardware and software architecture of the NVIDIA DGX Station A100

CO3 :: develop deep convolutional neural networks (CNNs) for image classification

CO4 :: apply autoencoders and pre-trained CNNs for data compression, and image processing
tasks

CO5 :: examine recurrent neural networks for modelling sequential data

CO6 :: evaluate generative adversarial networks (GANs), exploring their components, challenges
and applications

Unit I
Building Models with TensorFlow : Introduction to TensorFlow, Installation of TensorFlow,
TensorFlow ranks and tensors, TensorFlow's computation graphs, variables in TensorFlow, TensorFlow
optimizers, transforming tensors as multidimensional data arrays, visualization with Tensorboard,
Introduction of Deep Learning, Applications of Deep Learning
Unit II
Building Models with Keras : Introduction to keras, Keras installation, keras layers and models,
building a regression model, multi-layer Perceptron learning for classification, image classification with
keras, building text classification model, overfit and underfit, save and load model, hyperparameter
tuning
NVIDIA DGX Station A100 : Introduction, Hardware Architecture, DGX Station A100 Software
Stack, CUDA Toolkit, Future of AI with DGX Station A100
Unit III
Classifying images with deep convolutional neural networks : building blocks of convolutional
neural networks, determining the size of the convolution output, performing a discrete convolution in
2D, subsampling, putting everything together to build a CNN, implementing a deep convolutional
neural network using TensorFlow, Transfer learning with pre-trained CNN, data augmentation, image
segmentation, NVIDIA Command Line Tools and Utilities
Unit IV
Autoencoders and Pre-trained CNN : introduction to autoencoders, need for autoencoders,
architecture of autoencoder, properties and hyperparameter, types of autoencoders, data
compression using autoencoders, variational autoencoders
Unit V
Modeling sequential data using recurrent neural networks : modeling sequential data,
understanding the structure and flow of an RNN, computing activation in an RNN, challenges of
learning long-range interactions, implementing a multilayer RNN for sequence modeling in
TensorFlow, text classification with an RNN, text generation with an RNN, time series forecasting,
LSTM units, sequence classification with LSTM, stacked LSTM for sequence classification
Unit VI
Generative Adversarial Networks : introduction to generative models, overview of GAN structure,
discriminator, generator, building GAN, problems with GANs, CycleGAN, Adversarial FGSM, use of
docker, Model deployment on NVIDIA Server Using Streamlit framework

List of Practicals / Experiments:

List of Practicals
• Identify a real world deep learning problem and select a suitable dataset for the project.

• Loading and Visualizing Dataset for Deep Learning Projects

• Basic Data Preprocessing: Normalization, Standardization, and Handling Missing Data

• Splitting Data into Training and Test Sets for Model Training

• Implementing a Simple Neural Network for Binary Classification

Session 2024-25 Page:1/2


• Training a Feedforward Neural Network on a Simple Dataset

• Use Pretrained Models for Basic Image Classification

• Implement a Basic Convolutional Neural Network (CNN) for Image Classification

• Training an RNN Model for Text Classification Using Simple Sentences

• Building and Training an Autoencoder for Image Compression

• Evaluating a Model's Performance Using Accuracy

• Saving and Loading a Trained Deep Learning Model for Future Use

• Visualizing Activation Maps of a CNN Model to Understand Feature Learning

• Prepare and present comprehensive project report including problem statement, methods, results
and challenges

Text Books:
1. DEEP LEARNING by AMIT KUMAR DAS, Pearson Education India

References:
1. ADVANCED DEEP LEARNING WITH TENSORFLOW 2 AND KERAS by ROWEL ATIENZA,
PACKT PUBLISHING

Session 2024-25 Page:2/2

You might also like