Machine Learning

(3-5 Credit Hours) · Undergraduate

This module covers the core topics that dominate machine learning research: classification, clustering and reinforcement learning. We describe a variety of classification algorithms (e.g. Neural Networks, Decision Trees and Learning Classifier Systems) and clustering algorithms (e.g. k-NN and PAM) and discuss the practical implications of their application to real world problems. We then introduce reinforcement learning and the Q-learning problem and describe its application to control problems such as maze solving. DU - Dublin City University This course will cover introductory topics and conventional algorithms needed to understand the field of Machine Learning. The course will prepare students to understand and distinguish between main groups of methods used in Machine Learning, supervised and unsupervised, and how and when they are applicable. Key topics will include Regression, Decision Trees, Naive Bayes, Neural Networks, Clustering and Principal Component Analysis. HT- Hong Kong, China (HKUST) This course provides a comprehensive coverage of the machine learning field. It introduces the foundations of machine learning, such as optimization, regularization, and generalization. It covers several traditional machine learning algorithms and various types of neural networks, such as feedforward, convolutional, recurrent, and transformer models, as well as their applications to computer vision, natural language processing, and generative modelling. The course also includes selected advanced topics. Dublin, Ireland (IR): This module delves into advanced machine learning techniques central to modern artificial intelligence. Building upon foundational knowledge from "STAT30270 Statistical Machine Learning", students will explore advanced methods and models that enable accurate prediction and the ability to learn from complex, high-dimensional data. Key topics include (subject to changes): - Deep learning - Understanding and implementing neural networks, including convolutional and recurrent architectures, for processing data such as images, text, and time series. - High-dimensional data - Techniques for managing and extracting insights from large-scale datasets, with an emphasis on scalability and computational efficiency. - Model evaluation and benchmarking - Approaches to assess and compare predictive models to ensure robustness, generalizability, and performance. - Interpretability and uncertainty - Exploring the 'black-box' nature of complex models, including methods for model interpretation and quantifying predictive uncertainty. Practical sessions will involve hands-on experience with the R programming language and the Keras library, facilitating the application of concepts to real-world problems. By the end of the module, students will be equipped to design, implement, and critically evaluate advanced machine learning methods across various domains. Sydney, Australia (SY): Machine learning is the process of automatically building mathematical models that explain and generalise datasets. It integrates elements of statistics and algorithm development into the same discipline. Data mining is a discipline within knowledge discovery that seeks to facilitate the exploration and analysis of large quantities for data, by automatic and semiautomatic means. This subject provides a practical and technical introduction to machine learning and data mining. Topics to be covered include problems of discovering patterns in the data, classification, regression, feature extraction and data visualisation. Also covered are analysis, comparison and usage of various types of machine learning techniques and statistical techniques.