M.Sc. (Information Technology) Deep Learning Practical Syllabus - Mumbai University

• 1 Introduction to TensorFlow
• a • Create tensors with different shapes and data types. • Perform basic operations like addition, subtraction, multiplication, and division on tensors. • Reshape, slice, and index tensors to extract specific elements or sections. • Performing matrix multiplication and finding eigenvectors and eigenvalues using TensorFlow
• b Program to solve the XOR problem.
• 2 Linear Regression
• a • Implement a simple linear regression model using TensorFlow's low- level API (or tf. keras ). • Train the model on a toy dataset (e.g., housing prices vs. square footage). • Visualize the loss function and the learned linear relationship. • Make predictions on new data points.
• 3 Convolutional Neural Networks (Classification)
• a Implementing deep neural network for performing binary classification task
• b Using a deep feed-forward network with two hidden layers for performing multiclass classification and predicting the class.
• 4 Write a program to implement deep learning Techniques for image segmentation.
• 5 Write a program to predict a caption for a sample image using LSTM.
• 6 Applying the Autoencoder algorithms for encoding real-world data
• 7 Write a program for character recognition using RNN and compare it with CNN.
• 8 Write a program to develop Autoencoders using MNIST Handwritten Digits
• 9 Demonstrate recurrent neural network that learns to perform sequence analysis for stock OC2,OC3,OC4 price.(google stock price)
• 10 Applying Generative Adversarial Networks for image generation and unsupervised tasks.

Books and References

• 1 Deep learning with TensorFlow Giancarlo Zaccone Packt 2nd 2018 Md. Rezaul Karim
• 2 Zero to Deep Learning Francesco Mosconi Fullstack.io 1st 2019