SPRING2022-MASTER-COMPUTER-SCIENCE / repository

COMP-596-Machine-Learning

Department of Computer Science – Spring 2022 Bridgewater State University Course Description Machine Learning is the science of getting computers to act without being explicitly programmed and learn from experience; more specifically, its goal is to design algorithms that allow computers to learn from empirical data. Machine learning is an exciting interdisciplinary field, with historical roots in computer science, statistics, pattern recognition, and even neuroscience and physics. In the last decade, many of these approaches have converged and led to rapid theoretical advances and real-world applications. This course will provide a broad introduction to the machine learning techniques that have proven valuable and successful in discovering patterns and making predictions in practical applications and students will be able to implement and apply these techniques on solving real problems. This course will also contrast the various methods, with the aim of explaining the circumstances under which each is most appropriate. We will also discuss basic issues that confront any machine learning method. Credit no. & Course Type 3 credits (Elective) Class Location Dana Mohler Faria Sci Math Ctr (DMF) 363 Class Times COMP 399-Sec 01: 3:25 pm – 4:40 pm Tue and Thu COMP 596-Sec 01: 4:45 pm – 7:25 pm Thu Instructor Dr. Haleh Khojasteh Office Hours 2:00 pm – 3:00 pm Tue, Wed and Thu or by appointment Office Location DMF 341 E-Mail hkhojasteh@bridgew.edu; I will respond within 1-2 days. This is my preferred communication method. Course Site Blackboard Recommended Book Listed below Prerequisite For COMP 399: COMP 250 with a minimum grade of "C-" Recommended textbooks: • “Pattern Recognition and Machine Learning”, by Christopher M. Bishop. (2006, Springer). • “Deep Learning (Adaptive Computation and Machine Learning series)”, by Ian Goodfellow, Yoshua Bengio and Aaron Courville. (2016, MIT Press). • “Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems”, 2nd Edition, by Aurélien Géron. (2019, O'Reilly Media, Inc.) • “Understanding Machine Learning: From Theory to Algorithms”, by Shai Shalev-Shwartz and Shai Ben-David. (2014, Cambridge University Press) • “Machine Learning: A Probabilistic Perspective (Adaptive Computation and Machine Learning series)”, by Kevin P. Murphy. (2012, MIT Press) Course Goals and Outcomes Upon completion of this course, students will understand the most important machine learning techniques, and will be able to implement and apply these techniques on solving real problems: • Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks); • Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning); • Best practices in machine learning (bias/variance theory; innovation process in machine learning and AI). The course will also draw from numerous case studies and applications, so that students will also learn how to apply learning algorithms to building smart robots (perception, control), text understanding (web search, anti-spam), computer vision, medical informatics, audio, database mining, and other areas.