COMP3308 - HD Notes

Description

Includes 77 pages of comprehensive and organised subject notes for weeks 1 - 13 including worked examples and half a page to one-page lecture summaries at the end that cover the key learning objectives for each week. These notes helped me to achieve a high distinction in the final exam and in the course overall. For each week, I read the textbook and lecture notes prior to class, attended said lecture, and rewatched the lecture recording online to collate only the most important information (so you don't have to). The summaries at the end are dot points to give you an idea of what you should have taken away from that week's content. Topics Covered: - History of AI - Simple Search: DFS, BFS, UCS, IDS, Greedy - Complex Search: A*, Beam, Hill Climb, Simulated Annealing - Genetic Algorithms - Game Playing: Minimax, Expectiminimax, and Alpha-Beta Pruning - Machine Learning: Nearest Neighbour and 1-Rule - Naive Bayes Algorithm - Evaluation of Classifiers - Decision Trees - Perceptrons - Multilayer Perceptrons (including detailed backpropagation algorithm and deep neural networks) - Autoencoders and Convolutional Neural Networks - Support Vector Machines - Kernel Functions - Classifier Ensembles: Bagging, Boosting, Forests - Probability and Bayesian Networks - Unsupervised Learning Algorithms: Clustering - Recommender Systems I have found these notes useful even after the course finished so I trust if you have an interest in AI, these will last you well beyond the final.