Basics of Python
Module description This module discuss the basics of Python programming language and explore how to setup Python environment to work with machine learning. Demonstrate different parts of Python code such as keywords, variables, data types, statements, functions, loops, libraries and get familiarized with programming in python. Learning Outcomes LO1: Learn basic concepts of Python LO2: Acquire rudimentary skills to write programs in Python LO3: Ability to use Python for Data Science & Machine learning LO4: Get application-ready with essential Python libraries & tools Content Covered Basic Python Programming Variable and data types Conditional statements Loops Functions Essential Python libraries for data science Pandas Numpy Scikit Setting up Python for Machine Learning
Mathematics & Statistics for Machine Learning & Artificial Intelligence
Module Description Mathematics have a significant role in the foundation for programming and this module is designed to help students master the mathematical foundation required for writing programs and algorithms for Artificial Intelligence and Machine Learning. The module covers three main mathematical theories: Linear Algebra, Statistics and Probability Theory. Learning Outcomes LO1: Master the mathematical foundation required for writing programs LO2: Learn mathematical and statistical foundations required for AI & ML LO3: Acquire mathematical knowledge to build algorithms for data analysing LO4: Apply statistical analysis techniques using essential softwares on data sets Content Covered Linear Algebra Statistics Probability Theory Statistical Tools (CSV, Excel).
Python for Machine Learning
This module provides a comprehensive guide to Python programming and its data-oriented library ecosystem, focusing on equipping students with the skills to become effective data analysts. It covers essential libraries like NumPy, pandas, and Matplotlib. Students will learn practical data analyzing, handling, and visualization skills using Python tools, perform mathematical operations with NumPy, manipulate data with Pandas, and visualize data using Matplotlib. The module also introduces the basics of using Sci-kit-learn for data analysis.
Introduction to Machine Learning & Artificial Intelligence
This module explores artificial intelligence and machine learning techniques, including ML, DL, NLP, RL, and DRL. It covers real-world applications of algorithms like linear regression, k-NN, decision trees, and random forest for supervised, unsupervised, and reinforcement learning. Students will gain a strong foundation in AI and ML fundamentals, learn data pre-processing techniques, understand major ML algorithms (classifiers, regression, clustering), and develop critical thinking skills in analyzing established ML approaches. The content includes an introduction to ML and AI, supervised and unsupervised learning, reinforcement learning, machine learning algorithms, and the ML task process.
Specialisation Modules - Natural Language Processing (NLP) pathway
This module covers advanced Python for NLP, exploring mathematics and optimization for resilient machine learning systems. It teaches multivariate calculus and mathematical intuition in Natural Language processing, including synonyms, antonyms, text analysis, and tokenization using the Natural Language Toolkit package. The course enables learners to understand NLP concepts, acquire Python skills for NLP, write scripts for text pre-processing, and learn machine learning algorithms and computer vision tools.
Machine Learning for NLP
This module explores machine learning models and techniques for Natural Language Processing, covering supervised and unsupervised learning, text analysis, and the application of Python for algorithm implementation. It also includes traditional neural network learning methods like feed-forward, recurrent, and convolutional networks, focusing on problems in natural language processing. The learning outcomes include understanding deep learning using TensorFlow and Keras, text processing and vectorization, building NLP algorithms, and exploring various NLP concepts and applications. The content covered encompasses machine learning introduction, supervised and unsupervised learning, ML deployment, speech recognition, text-to-speech conversion, decision theory, regression, classification, text analysis, and computer vision.
Advanced Python for Computer Vision (CV)
This module covers numerical processing with NumPy, image manipulation with OpenCV, and deep learning with CNN & RNN models. It explores various image processing techniques, video handling, and computer vision using Python. The learning outcomes include understanding Python tools for computer vision, image processing packages, machine learning algorithms, and computer vision concepts. The content covers core Python, machine learning algorithms, and computer vision tools like Keras and TensorFlow.
Machine Learning for Computer Vision (CV)
This module explores machine learning methodologies for handling industrial challenges and diverse data mining activities. Learners delve into algorithms such as neural networks, k-means clustering, and support vector machines in computer vision. Concepts of deep learning, YOLO algorithms, and CNN and RNN models are developed for automated CV algorithms. The content covers CV introduction, deep learning network models, CNNs and RNNs, Keras model life-cycle, and image data manipulation using Python libraries like Pillow and NumPy.
Capstone Project - PG Level Project/Dissertation
This module examines the impact of Artificial Intelligence and Machine Learning in organizations, emphasizing their role in performance and competence. Learners undertake a research project to showcase expertise in AI & ML, covering areas like Machine Learning, Deep Learning, Natural Language Processing, and Computer Vision. It emphasizes the significance of AI & ML in organizational planning, decision-making, and change implementation, offering participants comprehensive knowledge for potential employers or educational programs. Learning outcomes include independent research, professional documentation, effective communication, and executing research-based projects autonomously with accountability.
