Machine Learning

COMP24112 Machine Learning 10 Semester 2 Undergraduate Level 2 Tingting Mu Unit coordinator Department of Computer Science 1 FHEQ level (Framework for Higher Education Qualifications) ' Middle part of Bachelors ' European Credit Transfer & Accumulation System Rating : 5.0 The unit will cover the following. A general introduction to key concepts in machine learning and the development of the field. Essential knowledge on how to build a supervised machine learning system, including classification and regression, with respect to model architecture (e.g., instance-based model, linear model, linear basis function model, kernel methods, single- and multi-layer perceptrons, convolutional neural network etc.), loss functions (e.g., sum of squares error, regularisation, cross-entropy, etc.), and optimisation approaches for training (e.g., basic optimality conditions, (stochastic) gradient descent, etc.). Basic knowledge on different types of machine learning models (e.g., parametric, non-parametric, deterministic and probabilistic models). Essential knowledge on clustering analysis for grouping similar objects. Essentials on how to measure performance of a machine learning system for classification, regression and clustering. Basics on machine learning phenomena like bias and variance issues, over-fitting and under-fitting. Essential knowledge and practical skills on how to perform machine learning experiments, and on data usage for model training, model selection and model testing. The teaching content is divided into ten chapters:•    Machine Learning Basics•    k-Nearest Neighbours•    Machine Learning Experiments•    Typical Machine Learning Models•    Loss Functions•    Training and Optimisation•    Artificial Neural Networks•    Deep Learning and Convolutional Neural Networks•    Unsupervised Learning•    Machine Learning ApplicationsThe course has a fair amount of mathematical and algorithmic content and is intended to be self-contained. The lab work is based on Python.  The unit will cover the following. A general introduction to key concepts in machine learning and the development of the field. Essential knowledge on how to build a supervised machine learning system, including classification and regression, with respect to model architecture (e.g., instance-based model, linear model, linear basis function model, kernel methods, single- and multi-layer perceptrons, convolutional neural network etc.), loss functions (e.g., sum of squares error, regularisation, cross-entropy, etc.), and optimisation approaches for training (e.g., basic optimality conditions, (stochastic) gradient descent, etc.). Basic knowledge on different types of machine learning models (e.g., parametric, non-parametric, deterministic and probabilistic models). Essential knowledge on clustering analysis for grouping similar objects. Essentials on how to measure performance of a machine learning system for classification, regression and clustering. Basics on machine learning phenomena like bias and variance issues, over-fitting and under-fitting. Essential knowledge and practical skills on how to perform machine learning experiments, and on data usage for model training, model selection and model testing. The teaching content is divided into ten chapters:•    Machine Learning Basics•    k-Nearest Neighbours•    Machine Learning Experiments•    Typical Machine Learning Models•    Loss Functions•    Training and Optimisation•    Artificial Neural Networks•    Deep Learning and Convolutional Neural Networks•    Unsupervised Learning•    Machine Learning ApplicationsThe course has a fair amount of mathematical and algorithmic content and is intended to be self-contained. The lab work is based on Python.  Machine learning is concerned with creating computational models that allow a computer to learn from data, e.g., to automatically analyse and identify patterns and make predictions. Typical applications include computer vision, natural language processing, speech synthesis and recognition, medical diagnostics, intelligent robots, vehicle autonomy, material sciences, etc. This unit aims to introduce the essential concepts behind key machine learning techniques, methodologies for building machine learning systems, algorithmic approaches for learning from data, and empirical methods on how to evaluate the performance of a learning system and to optimise its performance. Also, the unit aims to provide the necessary mathematical background required to understand how the machine learning methods work. It covers basics on supervised and unsupervised learning paradigms and is pitched towards students with scientific and mathematical background who are interested in adaptive techniques for learning from data and developing AI solutions.  ILO 1: Explain key clustering algorithms, how to evaluate their performance, and their applications.ILO 2: Identify and describe issues in machine learning.ILO 3: Describe fundamental concepts in machine learning (including supervised and unsupervised learning, classification, regression and clustering), and essential elements for building a machine learning system.ILO 4: Describe fundamental concepts in model training, validation, evaluation and selection, and apply the knowledge to use data, design machine learning experiments, and make observations from results.ILO 5: Design and implement machine learning solutions to real-world problems, evaluate the solution, analyse results and implication.ILO 6: Explain key supervised learning techniques, compare their differences (including limitations and advantages, quality and trade-offs, commercial/industrial concerns), and apply the knowledge to select suitable techniques for a particular application. Analytical skills Project management Problem solving Written communication The unit will cover the following. A general introduction to key concepts in machine learning and the development of the field. Essential knowledge on how to build a supervised machine learning system, including classification and regression, with respect to model architecture (e.g., instance-based model, linear model, linear basis function model, kernel methods, single- and multi-layer perceptrons, convolutional neural network etc.), loss functions (e.g., sum of squares error, regularisation, cross-entropy, etc.), and optimisation approaches for training (e.g., basic optimality conditions, (stochastic) gradient descent, etc.). Basic knowledge on different types of machine learning models (e.g., parametric, non-parametric, deterministic and probabilistic models). Essential knowledge on clustering analysis for grouping similar objects. Essentials on how to measure performance of a machine learning system for classification, regression and clustering. Basics on machine learning phenomena like bias and variance issues, over-fitting and under-fitting. Essential knowledge and practical skills on how to perform machine learning experiments, and on data usage for model training, model selection and model testing. The teaching content is divided into ten chapters:•    Machine Learning Basics•    k-Nearest Neighbours•    Machine Learning Experiments•    Typical Machine Learning Models•    Loss Functions•    Training and Optimisation•    Artificial Neural Networks•    Deep Learning and Convolutional Neural Networks•    Unsupervised Learning•    Machine Learning ApplicationsThe course has a fair amount of mathematical and algorithmic content and is intended to be self-contained. The lab work is based on Python.  <div>Weekly lectures with structured input and exploratory activities. These will be organised as a blend of brief presentations, tutorial question and practice activities, discussions of materials and tasks that are available online, and question-answer sessions.  Bi-weekly laboratories will be drop-in help desks where GTAs provide support for problems provided in lab scripts. These will also be used as surgeries to provide feedback on assessments and as an opportunity to ask questions about the set tasks, and learning materials. Lab scripts contain assessments on mathematical programming for supporting basic machine learning model implementation, also design, implementation and analysis of machine learning techniques for real-world applications.</div> 1 Written exam 80% 8 Practical skills assessment 20% Cohort-level feedback after marking and individual feedback provided by GTA upon request. COMP11120 Mathematical Techniques for Computer Science Pre-Requisite Compulsory MATH11121 Mathematical Foundations & Analysis Pre-Requisite Compulsory COMP11120 (for CS students) and MATH11121 or equivalent (for CM students).COMP11120 (for CS students) and MATH11121 or equivalent (for CM students). Y <ol><li>Bishop, Christopher M. (2006). Pattern recognition and machine learning. Springer. ISBN:<a href="https://www.librarysearch.manchester.ac.uk/discovery/search?query=isbn,contains,9780387310732&search_scope=MyInst_and_CI&sortby=rank&vid=44MAN_INST:MU_NUI&lang=en&mode=advanced&offset=0" target="_blank"> 9780387310732</a>  </li><li>Alpaydin, Ethem. (2014). Introduction to machine learning. The MIT Press. ISBN:<a href="https://www.librarysearch.manchester.ac.uk/discovery/search?query=isbn,contains,9780262325745&search_scope=MyInst_and_CI&sortby=rank&vid=44MAN_INST:MU_NUI&lang=en&mode=advanced&offset=0" target="_blank"> 9780262325745</a>  </li><li>Murphy, Kevin P. (2012). Machine learning: a probabilistic perspective. MIT Press. ISBN:<a href="https://www.librarysearch.manchester.ac.uk/discovery/search?query=isbn,contains,9780262305242&search_scope=MyInst_and_CI&sortby=rank&vid=44MAN_INST:MU_NUI&lang=en&mode=advanced&offset=0" target="_blank"> 9780262305242</a>  </li><li>Mitchell, Tom M. (1997). Machine learning. WCB/McGraw-Hill. ISBN:<a href="https://www.librarysearch.manchester.ac.uk/discovery/search?query=isbn,contains,0070428077&search_scope=MyInst_and_CI&sortby=rank&vid=44MAN_INST:MU_NUI&lang=en&mode=advanced&offset=0" target="_blank"> 0070428077 </a></li></ol> Assessment written exam 2 Lectures 22 Practical classes & workshops 12 0 64