Course information

 1.     Module Code: MIT91207    School: Graduate School

 2.     Module Title: Machine Learning

 3.     Year: 1        Trimester: 1     Credits: 10

 

Brief Description of Aims and Content

Machine learning is the science of getting computers to act without being explicitly programed. This course provides a broad introduction to machine learning and statistical pattern recognition. In this course, students will learn about the most effective machine learning techniques, and gain practice implementing them and getting them to work. Students not only learn the theoretical underpinnings of learning, but also gain the practical know-how needed to quickly and powerfully apply these techniques to new problems.

The course will also discuss recent applications of machine learning, such as, data mining, autonomous navigation, speech recognition, and text and web data processing. The course will also draw from numerous case studies and applications, so student also learn how to apply learning algorithms to building gesture-based and multimodal interfaces, text and speech understanding (web search, anti-spam), smart robots, medical informatics, audio, database mining and other areas.

Indicative Content:

Foundations: Introduction to Artificial Intelligence (AI) and Machine Learning, Key techniques and paradigms in ML, Data preprocessing and feature engineering. Supervised Learning:  Classification and regression models, Parametric and non-parametric methods, Support Vector Machines and kernel methods, Neural networks and deep feedforward models. Unsupervised Learning: Clustering techniques, Dimensionality reduction (PCA, t-SNE, autoencoders), Recommender systems. Best Practices in ML: Bias–variance trade-off and model generalization, Hyperparameter tuning and model selection, Innovation processes in ML and AI.  Deep Learning and Advanced Topics: Introduction to deep learning and GPU computing, Neural networks with TensorFlow/PyTorch, Analysis of streaming data with TensorFlow, Image processing and OCR applications, Speech recognition and natural language processing, Real-time large-scale ML systems. Applied Machine Learning: Pattern recognition and decision systems,  Question-answering and intelligent agents, Search engines and PageRank-like systems, Large-scale information retrieval (text, images, sound, video),  Comparative study of technologies for processing high-velocity data.