Applied Artificial Intelligence and Machine Learning

Course Overview

This is course is designed to delve into the intricacies of deep learning, focusing on cutting-edge applications and architectures. The course emphasises the practical application of deep learning techniques, particularly in handling image data using convolutional neural networks (CNNs). Students will explore a variety of deep learning frameworks and gain hands-on experience through detailed case studies that showcase the implementation of these technologies in real-world scenarios. From recognising visual patterns to enhancing image processing capabilities, the course offers a thorough examination of how deep learning can be leveraged to solve complex problems in various domains, preparing students for innovative challenges in the field of AI and ML.

• Deep Learning Foundation
• Neural Network
• Advanced Cnn Architectures
• Transformers And Their Applications

Prerequisites

• Must have completed 1 of ARTI5002 Applied Artificial Intelligence and Machine Learning/ARTI6003 Machine Learning Algorithms

Textbooks

• Primary: “Machine Learning: A Probabilistic Perspective” by Kevin Murphy
• Reference: “Pattern Recognition and Machine Learning” by Christopher Bishop

Grading

• Assignments: 75%
• Open book quizes: 10%
• Close book quizes: 15%

Schedule

Week	Date	Topic	Materials
1	June 1	Introduction to Deep Learning Overview of deep learning, course structure, and expectations.	Syllabus Lecture Notes Coding Lab
2	June 8	Neural Network Optimization Introduction to gradient descent, overfitting and regularization.	Lecture Notes Coding Lab Quiz 1
3	June 15	Introduction to Convolutional Neural Networks Convolution and multi-class classification.	Lecture Notes Coding Lab In-class Quiz 1 Assignment 1
4	June 22	CNN Architecture Pooling and LeNet.	Lecture Notes Coding Lab Quiz 2
5	June 29	Modern Applications Introduction of Architecture.	Lecture Notes Coding Lab
6	July 6	Alexnet and VGG Advancing ANN design with repitive blocks.	Lecture Notes Coding Lab Quiz 3
7	July 13	GoogLeNet, ResNet and Densenet Inception, residual learning and dense connectivity.	Lecture Notes Coding Lab Assignment 2
8	July 20	Sequence Modeling and Attention Mechanisms Attention mechanism and multi-head attention.	Lecture Notes Coding Lab Quiz 4 In-class Quiz 2
9	July 27	Transformer Transformer and Vistion transformer.	Lecture Notes Coding Lab
10	Aug 3	LLM From transformer to LLM.	Lecture Notes Coding Lab Quiz 5 In-class Quiz 3 Assignment 3