DEEP LEARNING USING PYTHON PROGRAMMING

COURSE OBJECTIVES:
 To understand and need and principles of deep neural networks
 To understand CNN and RNN architectures of deep neural networks
 To comprehend advanced deep learning models
 To learn the evaluation metrics for deep learning models

UNIT I INTRODUCTION TO DEEP LEARNING

Introduction to Deep Learning--Bayesian Learning --Decision Surfaces-- Linear Classifiers,

Linear Machines with Hinge Loss-- Optimization Techniques-- Gradient Descent -- Batch
Optimization-- Neural Network.

UNIT II DEEP NETWORKS

Linear Algebra: Scalars -- Vectors -- Matrices and tensors; Probability Distributions -- Gradient-
based Optimization – Machine Learning Basics: Capacity -- Overfitting and underfitting – Hyper
parameters and validation sets -- Estimators -- Bias and variance -- Stochastic gradient descent
-- Challenges motivating deep learning; Deep Networks: Deep feed forward networks;
Regularization -- Optimization.

UNIT III CONVOLUTIONAL NEURAL NETWORKS

Convolution Operation -- Sparse Interactions -- Parameter Sharing -- Equivariance -- Pooling --
Convolution Variants: Strided -- Tiled -- Transposed and dilated convolutions; CNN Learning:
Nonlinearity Functions -- Loss Functions -- Regularization -- Optimizers --Gradient Computation.

UNIT IV Python Basics, Objects-

Python Objects-Standard Types-Other Built-in Types- Numbers -Introduction to Numbers-
Integers, Floating Point Real Numbers-Strings, Lists, and Tuples, Mapping and Set Types.

UNIT V Files:
File Objects, File Built-in Function [ open() ], Methods,Attributes, Standard Files, Command-line
Arguments, File System, File Execution, Persistent Storage Modules, Related Modules.
Exceptions in Python, Detecting and Handling Exceptions, Context Management,Exceptions as
Strings, Raising Exceptions,Creating Exceptions.

UNIT VI Modules:
Modules and Files, Namespaces, Importing Modules, Importing Module Attributes, Module Built-
in Functions, Packages, Other Features of Modules.GUI Programming: Introduction, Tkinter and
Python Programming, Brief Tour of Other GUIs, Related Modules and Other GUIs. WEB
Programming:Introduction, Wed Surfing with Python, Creating Simple Web Clients, Advanced
Web Clients, CGI-Helping Servers Process Client Data, Building CGI Application.
TOTAL: 60 PERIODS
TEXT BOOK
1. Ian Goodfellow, Yoshua Bengio, Aaron Courville, ``Deep Learning'', MIT Press, 2016.
2. Andrew Glassner, “Deep Learning: A Visual Approach”, No Starch Press, 2021.
3. Introduction to Python, Kenneth A. Lambert, Cengage
4. Python Programming: A Modern Approach, Vamsi Kurama, Pearson
5. Learning Python, Mark Lutz, O’Really.

REFERENCES
1. Salman Khan, Hossein Rahmani, Syed Afaq Ali Shah, Mohammed Bennamoun, ``A Guide to
Convolutional Neural Networks for Computer Vision'', Synthesis Lectures on Computer Vision,
Morgan & Claypool publishers, 2018.
2. Yoav Goldberg, ``Neural Network Methods for Natural Language Processing'', Synthesis
Lectures on Human Language Technologies, Morgan & Claypool publishers, 2017.
3. Francois Chollet, ``Deep Learning with Python'', Manning Publications Co, 2018.
4. Charu C. Aggarwal, ``Neural Networks and Deep Learning: A Textbook'', Springer
International Publishing, 2018.