Machine Learning & Optimisation Techniques

EEEN40151 Machine Learning & Optimisation Techniques 15 Semester 1 Undergraduate Level 4 Hujun Yin Unit coordinator Khairi Hamdi Unit coordinator 1 FHEQ level (Framework for Higher Education Qualifications) ' Masters/Integrated Masters P4 ' European Credit Transfer & Accumulation System Rating : 7.5 (1) Introduction of convex sets and convex functions(2) Illustrate convex optimization problems, including linear programming, quadratic programming, geometric programming, semi-definite programming(3) Introduce duality theory, including Lagrangian dual function, Lagrange dual problem, weak and strong duality, Interpretation of dual variables, KKT optimality conditions.(4) Illustrate various convex optimization methods and algorithms, such as descent methods, Newton methods, sub-gradient method, interior point method,  (5) Provide some applications of convex optimization to signal processing and communications(6)  Introduction to machine learning and optimisation.(7) High-dimensional data representation. Basic multivariate statistical and regression models. Decision tree algorithms and Bayesian learning.(8) Clustering and classification algorithms including SVMs.(9) Introduction to neurons, human visual system and neural networks. Artificial neural networks (feedforward, recurrent) and their learning mechanisms: supervised and unsupervised.(10) Introduction to deep learning neural networks and their implementations. (1) Introduction of convex sets and convex functions(2) Illustrate convex optimization problems, including linear programming, quadratic programming, geometric programming, semi-definite programming(3) Introduce duality theory, including Lagrangian dual function, Lagrange dual problem, weak and strong duality, Interpretation of dual variables, KKT optimality conditions.(4) Illustrate various convex optimization methods and algorithms, such as descent methods, Newton methods, sub-gradient method, interior point method,  (5) Provide some applications of convex optimization to signal processing and communications(6)  Introduction to machine learning and optimisation.(7) High-dimensional data representation. Basic multivariate statistical and regression models. Decision tree algorithms and Bayesian learning.(8) Clustering and classification algorithms including SVMs.(9) Introduction to neurons, human visual system and neural networks. Artificial neural networks (feedforward, recurrent) and their learning mechanisms: supervised and unsupervised.(10) Introduction to deep learning neural networks and their implementations. The unit aims to:(1) To provide a general overview of convex optimization theory and its applications.(2) To introduce various classical convex optimization problems and illustrate how to solve these numerically and analytically.  (3) To introduce and practise basic machine learning techniques for multivariate data analysis and engineering applications.(4)  To introduce and practise fundamental neural networks and their recent advances, esp. deep learning neural networks and implementations in practical applications. On successful completion of the course, a student will be able to:ILO 1: Understand the motivation and benefit of using convex optimization and machine learningILO 2: Establish a good understanding about convex sets and convex functionsILO 3: Recognise typical forms of convex optimizations and their associated optimal solutionsILO 4: Understand fundamental machine learning approaches in problem solvingILO 5: Able to apply machine learning methods in practical data-oriented problemsILO 6: Understand neural networks and basic deep learning networks and their applications    <ul><li>To be able to reason about situations arising in the use of optimization and machine learning</li><li>To be able to design algorithms for obtaining optimal solutions for convex optimization problems</li><li>To be able to apply problem solving approaches used in machine learning and neural networks in wider engineering tasks</li><li>To be able to design a machine learning or neural network algorithm or system for a given learning problem</li></ul> <ul><li>To be able to apply convex optimization to practical communication systems</li><li>To be able to use machine learning tools or libraries in practical applications</li></ul> <ul><li>Develop the capability for mathematical and algorithmic formulation</li><li>Develop wider problem-solving and data analytical skills in engineering</li><li>Scientific report writing and presentation</li></ul> 0 Other 30% 1 Written exam 70% Examination Duration: 3 hours. (70%)Coursework Machine Learning Coursework (15%) Optimisation Techniques (15%) . EEEN30101 Numerical Analysis Pre-Requisite Recommended N Lectures 27 Practical classes & workshops 18 Tutorials 6 0 99