Artificial Intelligence and Machine Learning

Course Objective: 

The objective of this course is to familiarise the students with basic philosophy of artificial intelligence and machine learning, teach the mathematical tools used for machine learning algorithms, and teach how-to-use open-source machine learning softwares.

Learning Outcome: 

LO-1: The students will be able to learn the basic mathematical and computational tools of machine learning.

LO-2: The student will become familiarised with using public data-set, loading them in open-source ML tools categorise the data and test efficiency of their models.

Course Content: 

Unit I: Basic concepts of Machine Learning

Philosophy of Artificial Intelligence 

Machine Learning and its applications

Familiarization with the numerical tools

Various training models

Linear regression theory

Gradient descent

Polynomial regression

Logistic regression

Image classification

Image processing

Text processing

Introduction to Genetic Programming

Unit II: Hands-on implementation on open-source platforms.

Introduction to Computer Vision

Detecting Features in Images

Convolutions

Pooling

Implementing Convolutional Neural Networks.

Using Public Datasets with TensorFlow Datasets

Recurrent Neural Networks

Course Evaluation:

Internal Test 1  (25 Marks) 

Internal Test 2 (25 Marks)

Internal Test 3 (25 Marks)

Final Exam (50 Marks)

Final evaluation sheet will be prepared using the best TWO out of the three Internal Tests (25+25 = 50 Marks) + Final Exam (50 Marks).

Textbooks:

Deep Learning with Python, François Chollet

AI and Machine Learning for Coders by Laurence Moroney

Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, by Aurélien Géron

Genetic Programming, J R Koza

Fundamentals of Data Science - Theory & Practice, Kalita, Bhattacharyya, Roy; Academic Press, Elsevier, USA