Review of Machine Learning: Supervised, Unsupervised, Reinforcement Learning. Linear & Logistic Regression. Parameter setting of Neural Networks via Supervised Learning, Back-Propagation Algorithm
Unsupervised Learning: K-Means Clustering, Principal Components Analysis (PCA)
Machine Learning and Statistical Mechanics Concepts: Markov Chains definitions and classification of states. Chapman-Kolmogorov equations, asymptotic behavior, irreducibility recurrence, ergodicity, invariant probabilities. Markov Chain Monte Carlo methods, Metropolis-Hastings algorithm, Simulated Annealing, Gibbs Sampling. Generative models, Boltzmann Machine, Restricted Boltzmann Machine (RBM), Deep Belief Networks (DBN)
Control of Markov Systems, Dynamic Programming: Markov Decision Processes, Bellman’s Optimality Criterion, optimization algorithms – Value Iteration & Policy Improvement. Approximate dynamic programming methods, Q-Learning
Hidden Markov Models: The Viterbi algorithm, parameter estimation of hidden Markov Chains
Laboratory Exercises
Students are required to practice via Python based exercises at the PC Lab of the Electrical & Computer Engineering School of NTUA
Instructor
Vasilis Maglaris (Professor of the School of Electrical & Computer Engineering, NTUA)
Lab Assistants
Nikos Kostopoulos, Dimitris Pantazatos (Doctoral Candidates at the Network Management & Optimal Design Lab - NETMODE, School of Electrical & Computer Engineering, NTUA)
Suggested References
Simon Haykin, “Neural Networks and Learning Machines”, Third Edition, Pearson Education, 2009
Kevin P. Murphy, “Machine Learning: A Probabilistic Perspective”, MIT Press, 2012
Ian Goodfellow, Yoshua Bengio, Aaron Courville, “Deep Learning”, MIT Press, 2016
Daniel Jurafsky, James H. Martin, “Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition”, Third Edition draft, 2018
Andrew Ng, "CS229 Lecture Notes", Stanford University, Fall 2018, http://cs229.stanford.edu/notes/cs229-notes1
Frank Kelly, "Reversibility and Stochastic Networks", Wiley 1979, http://www.statslab.cam.ac.uk/~frank/BOOKS/book/whole.pdf
James Gareth, Daniela Witten, Trevor Hastie, Robert Tibshirani, “An Introduction to Statistical Learning with Applications in R”, Springer 2013, https://www-bcf.usc.edu/~gareth/ISL/ISLR%20First%20Printing.pdf