Coronavirus (Covid-19): Latest updates and information
Skip to main content Skip to navigation

Artificial Intelligence & Machine Learning

Pre-requisite

Pre-requisite for this module is Data Engineering with Python module

Introduction

In today's world, artificial intelligence and data science are powering innovation in virtually all industries and domains. The ability to build machines, and algorithms, that are able to reason and make decisions autonomously offers not only huge benefits to modern business, but to society as a whole. This module provides a hands-on exposure to the practice of developing AI/machine learning algorithms and implementing them in a variety of problem sets and datasets.

This module aims to enable participants to select, implement and evaluate machine learning algorithms in data science. In particular, the module highlights several of the most common, and in-demand, modern algorithms including ensemble methods and deep learning. Alongside technical knowledge, participants should develop an understanding of the applicability of different types of artificial intelligence & machine learning to common problems, and best practice for data science and Big Data analytics projects.

Objectives

Upon successful completion participants will be able to:

  • Interpret and evaluate various use-cases and the applicability of artificial intelligence and machine learning.
  • Comprehensive understanding of best practices for data processing and feature engineering for artificial intelligence and machine learning models.
  • Implement, interpret and critique current, professional standard learning models.
  • Automate deployment-ready machine learning pipelines and algorithms.
  • Evaluate and interpret the results of machine learning models and tune them to optimise performance.

Syllabus

  • Core concepts of Artificial Intelligence & Machine Learning
  • Data pre-processing & feature engineering
  • Na├»ve Bayes
  • Decision Trees
  • Support Vector Machines
  • Linear models
  • Ridge Regression
  • Lasso Regression
  • Gaussian Processes
  • Stochastic Gradient Decent
  • Ensemble Methods (Bagging/Boosting/Stacking)
  • Deep Learning
  • Artificial Neural Networks
  • Deep Neural Networks
  • Convultional Neural Networks
  • Recurrent Neural Networks & Long-Short Term Memory
  • Model training and evaluation

Assessment

  • Algorithm Development (20%)
  • Modeling Code (10%)
  • Post Module Assessment (70%)

Duration

2 weeks including 18 hours of lectures, 9 hours of seminars and 18 hours of supervised practical classes