L T P C Hrs
Deep Learning
Course Objectives
Understand Deep Learning – Gain foundational knowledge of deep learning
concepts, differences from machine learning, and its real-world applications.
Explore Neural Networks – Learn perceptron models, multi-layer perceptrons
(MLPs), and their mathematical representations.
Analyze Learning Mechanisms – Study activation functions, loss functions,
gradient descent, and backpropagation for training neural networks.
Apply CNNs and RNNs – Understand convolutional and recurrent neural networks,
their architectures, and applications in image and sequence data.
Implement LSTMs – Explore long short-term memory networks to overcome
limitations of RNNs in handling long-term dependencies.
Course Outcomes:
CO1 - Demonstrate understanding of Python basics, variables, operators, and
interactive programming.
CO2 - Implement control structures, data structures (lists, tuples, dictionaries), and
file operations effectively.
CO3 - Apply Python libraries (Pandas, Matplotlib, Scikit-Learn) for data analysis,
visualization, and regression tasks.
CO4 - Analyze and solve problems using regression techniques and evaluate model
performance with case studies.
CO5 - Design and implement machine learning algorithms such as Support Vector
Machines and Random Forests for predictive modeling.
Unit I GETTING STARTED WITH PYTHON PROGRAMMING (9 Hrs)
Introduction to Python - What is Python? - Advantages and Disadvantages - Downloading
and Installing - Python Versions - Running Python Scripts - Using the interpreter
interactively Using variables - String types: Normal Raw and Unicode - String Operators
and Functions - Math Operators and Functions - Writing to the screen.
Unit II CONTROL FLOW & DATA STRUCTURES IN PYTHON (9 Hrs)
Deep Dive into Python - Reading from the keyboard - Indenting is significant - Boolean -
The if and elif statements - While Loops - Using Lists - Dictionaries - Using the ‘for’
statement - Tuples - Opening Reading and Writing a Text File.
Unit III PYTHON LIBRARIES & ERROR HANDLING (9 Hrs)
Python Libraries - Using Pandas–the Python Data Analysis Library - Series and Data
Frames - Grouping Aggregating and Applying - Merging and Joining. Error Handling -
Dealing with Syntax Errors – Exceptions.
Unit IV ADVANCED TOPICS & REGRESSION (9 Hrs)
Other Topics - RE objects - Pattern Matching - Parsing Data. Regression (Use Case Study)
- Introduction to Regression - Why use Regression Analysis? - Types of Regression.
Unit V REGRESSION & MACHINE LEARNING (9 Hrs)
Other Regression Related Topics - Exploratory Data Analysis - Correlation Matrix -
Visualizations using Matplotlib - Implementing Linear Regression - Use Case: Churn
Analysis - Implementing Linear Regression (using Scikit Learn) - Results of Linear
Regression. Advance - Machine Learning Algorithms - Support Vector Machine - Random
Forest - Glossary.
Text Book:
1 Software Foundation Course with Python Programming © Copyright International
Business Machines Corporation 1993, 2009. US Government Users Restricted Rights
– Use, duplication or disclosure restricted by GSA ADP Schedule Contract with IBM
Corp.
References:
1 E Balagurusamy., “Python programming concepts”, Tata McGraw-Hill 2015, India.
2 Robert Lafore, “Programming in Python”, Waite Group, December 2013.
3 Herbert Schildt, “Python - The Complete Reference”, Tata McGraw-Hill 2014, New
Delhi.
4 Bjarne Stroustrup: “The Python Programming Language” (4th Edition). Addison-
Wesley. May 2012.
5 Elements of Programming Interviews in Python: The Insiders' Guide, 2nd edition by
15 September 2016.
COs/POs/ PSOs Mapping:
Program Specific
Program Outcomes (POs)
Outcomes (PSOs)
COs
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PSO1 PSO2 PSO3
1 3 2 1 1 3 1 1 2 2 1 3 3 1 2
2 3 3 2 2 3 1 1 2 2 2 3 3 2 2
3 3 3 2 3 3 2 1 2 2 2 3 3 3 2
4 3 3 3 3 3 2 2 2 2 2 3 3 3 2
5 3 3 3 3 3 2 2 2 2 2 3 3 3 3
Correlation Level: 1-Low, 2-Medium, 3- High