Learning Outcomes

To provide awareness of the two most integral branches (i.e. supervised & unsupervised learning) coming under Machine Learning

Describe intelligent problem-solving methods via appropriate usage of Machine Learning techniques.

To build appropriate neural models from using state-of-the-art python framework.

To build neural models from scratch, following step-by-step instructions.

To build end - to - end solutions to resolve real-world problems by using appropriate Machine Learning techniques from a pool of techniques available.

To critically review and select the most appropriate machine learning solutions

To use ML evaluation methodologies to compare and contrast supervised and unsupervised ML algorithms using an established machine learning framework.

Beginners guide for python programming is also inclusive.

Indicative Module Content

Introduction to Machine Learning:- What is Machine Learning ?, Motivations for Machine Learning, Why Machine Learning? Job Opportunities for Machine Learning

Setting up the Environment for Machine Learning:-Downloading & setting-up Anaconda, Introduction to Google Collabs

Supervised Learning Techniques:-Regression techniques, Bayer’s theorem, Naïve Bayer’s, Support Vector Machines (SVM), Decision Trees and Random Forest.

Unsupervised Learning Techniques:- Clustering, K-Means clustering

Artificial Neural networks [Theory and practical sessions - hands-on sessions]

Evaluation and Testing mechanisms :- Precision, Recall, F-Measure, Confusion Matrices,

Data Protection & Ethical Principles