Machine Learning for Signal Processing

Semester - Aug-Dec Type - Elective Credits - 3:1 Instructor - Sriram Ganapathy

Course Objectives - The goal of this course is to develop techniques which can enable machines to understand complex real-world signals like text, speech, images, videos etc. This course will cover methods which analyze, classify and detect the underlying information modalities present in real-world signals. This course consists of descriptions of signal processing tools for learning patterns in image and speech signals as the description of a class of machine learning tools which have been successfully used for these signals. There will be an emphasis on the application to image and speech recognition with roughly about 25% of the course driven from this perspective. This will be enforced by a final project submission on one of these applications.

Syllabus - Introduction to real world signals - text, speech, image, video. Feature extraction and front-end signal processing - information rich representations, robustness to noise and artifacts, signal enhancement, bio inspired feature extraction. Basics of pattern recognition, Generative modeling - Gaussian and mixture Gaussian models, hidden Markov models, factor analysis and latent variable models. Discriminative modeling - support vector machines, neural networks and back propagation. Introduction to deep learning - convolutional and recurrent networks, pre-training and practical considerations in deep learning, understanding deep networks. Clustering methods and decision trees. Decoding time sequences with finite state networks. Feature and model adaptation methods. Feature selection methods. Applications in computer vision and speech recognition.

Grading Details Assignments (10%) Midterm exam. (20 %) Final exam. (50 %) Project (20 %)

Pre-requisites 1. Random Process/Probablity and Statistics 2. Linear Algebra/Matrix Theory 3. Basic Digital Signal Processing/Signals and Systems

Textbooks a. “Pattern Recognition and Machine Learning”, C.M. Bishop, 2nd Edition, Springer, 2011. b. “Deep Learning”, I. Goodfellow, Y, Bengio, A. Courville, MIT Press, 2016. c. “Digital Image Processing”, R. C. Gonzalez, R. E. Woods, 3rd Edition, Prentice Hall, 2008. d. “Fundamentals of speech recognition”, L. Rabiner and H. Juang, Prentice Hall, 1993.

References i. “Deep Learning : Methods and Applications”, Li Deng, Microsoft Technical Report. ii. “Automatic Speech Recognition - Deep learning approach" - D. Yu, L. Deng, Springer, 2014. iii. “Computer Vision: Algorithms and Applications”, R. Szeliski, Springer, 2010.