Statistics & Machine Learning 2: AI, Complex Data, Computationally Intensive Statistics

DATA70132 Statistics & Machine Learning 2: AI, Complex Data, Computationally Intensive Statistics 15 Semester 2 Postgraduate Taught Level 7 Lorenzo Pellis Unit coordinator Social Statistics Department of Computer Science Department of Mathematics 1 FHEQ level (Framework for Higher Education Qualifications) ' Masters/Integrated Masters P4 ' European Credit Transfer & Accumulation System Rating : 7.5 The module is delivered as a mixture of lectures and practical sessions and has five main sections: <ol> <li style="margin-left:8px">Dimension reduction and feature extraction: principal components analysis, feature selection, information theory. </li> <li style="margin-left:8px">Classifiers and clustering: supervised and unsupervised learning, k-means and k-nearest neighbours, agglomerative clustering and dendrograms, support vector machines, linear and quadratic discriminants, Gaussian process classification, model-based clustering, mixture models and the EM algorithm. </li> <li style="margin-left:8px">Neural Networks and Deep Learning: perceptrons, back-propagation and multi-layer networks.</li> <li style="margin-left:8px">Markov-chain Monte Carlo (MCMC) methods:  Markov chains and their stationary distributions, likelihood-based inference using the Metropolis-Hastings algorithm, likelihood-free inference using Approximate Bayesian Computation, tests for convergence, applications to Bayesian inference.</li> <li style="margin-left:8px">Special Topic: Depending on the teaching staff, one special topic will be chosen to go into near-research depth, e.g. Random Forests; Social Networks; Time Series Analysis; Advanced Monte Carlo methods.</li></ol> The module is delivered as a mixture of lectures and practical sessions and has five main sections: <ol> <li style="margin-left:8px">Dimension reduction and feature extraction: principal components analysis, feature selection, information theory. </li> <li style="margin-left:8px">Classifiers and clustering: supervised and unsupervised learning, k-means and k-nearest neighbours, agglomerative clustering and dendrograms, support vector machines, linear and quadratic discriminants, Gaussian process classification, model-based clustering, mixture models and the EM algorithm. </li> <li style="margin-left:8px">Neural Networks and Deep Learning: perceptrons, back-propagation and multi-layer networks.</li> <li style="margin-left:8px">Markov-chain Monte Carlo (MCMC) methods:  Markov chains and their stationary distributions, likelihood-based inference using the Metropolis-Hastings algorithm, likelihood-free inference using Approximate Bayesian Computation, tests for convergence, applications to Bayesian inference.</li> <li style="margin-left:8px">Special Topic: Depending on the teaching staff, one special topic will be chosen to go into near-research depth, e.g. Random Forests; Social Networks; Time Series Analysis; Advanced Monte Carlo methods.</li></ol> The unit aims to introduce students to a selection of modern methods widely used in Data Science that can go beyond standard statistical frameworks. It builds on the foundation laid in Statistics and Machine Learning 1 and is strongly focussed on applications, aiming to train students to be informed users of existing algorithms. Students should be able to: <ul> <li style="margin-left:8px">Define the key terms from each of the module’s five sections</li> <li style="margin-left:8px">Understand when to apply a given learning algorithm and how to judge its success, including questions of convergence and computational performance.</li> <li style="margin-left:8px">Construct classifiers that capture features of already-understood data and exploit them to classify new data (supervised learning)</li> <li style="margin-left:8px">Use classification algorithms to discover and exploit previously-unknown structure in data (unsupervised learning).</li> <li style="margin-left:8px">Construct and train neural networks.</li> <li style="margin-left:8px">Use MCMC methods to estimate parameters and quantify uncertainty.</li> <li style="margin-left:8px">Present results, justifying choices of algorithm and communicating effectively with both technical and non-technical audiences.</li></ul> The five sections of this module are essentially self-contained subunits. Each consists of a series of lectures that introduce key concepts and serve as support for practical sessions in which the students apply python-based software tools to data analysis problems. 1 Written exam 80% 2 Written assignment (inc essay) 20% Feedback will be made available through Turnitin DATA70121 Statistics and Machine Learning 1: Statistical Foundations Pre-Requisite Compulsory DATA70121 is a pre-requisite for DATA70132 MSc Data Science MSc Data Science (Soc Analyt) PGDT Taught Component Mandatory MSc Data Science MSc Data Science (AUA) PGDT Taught Component Mandatory MSc Data Science MSc Data Science (Bus & Man) PGDT Taught Component Mandatory MSc Data Science MSc Data Science (Mathematics) PGDT Taught Component Mandatory MSc Data Science MSc Data Science (CSDI) PGDT Taught Component Mandatory MSc Data Science MSc Data Science (EA) PGDT Taught Component Mandatory N  <ul> <li>Simon Rogers & Mark Girolami (2017), A First Course in Machine Learning, 2nd edition, Chapman & Hall/CRC. ISBN 9781498738484</li> <li>Christopher Bishop (2006), Pattern Recognition and Machine Learning, Springer-Verlag, New York. ISBN: 9780387310732</li> <li>S. Brooks, A. Gelman, G. Jones, and X.-L. Meng, eds. (2011), Handbook of Markov Chain Monte Carlo, Chapman and Hall/CRC. ISBN: 9781420079418</li> <li>G. James, D. Witten, T. Hastie, and R. Tibshirani (2013), An Introduction to Statistic Learning with Applications in R. Springer-Verlag, New York. ISBN 9781461471370</li> <li>Trevor Hastie, Robert Tibshirani and Jerome Friedman (2009), The Elements of Statistical Learning: Data Mining, Inference, and Prediction. 2nd edition, Springer-Verlag. ISBN: 9780387848587</li></ul>  0 0 0