When  MW 3:30  5:00 pm 
Where  EE B308 
Who  Sriram Ganapathy 
Office  C 334 (2nd Floor) 
sriramg aT iisc doT ac doT in  
Teaching Assistant  Prachi Singh 
Lab  C 328 (2nd Floor) 
prachisingh aT iisc doT ac doT in 
Announcements
 MLSP practice for Final Exam Posted
 MLSP Final Exam Nov. 29 [130pm  430pm], B308, Classroom
 MLSP Project Final Evaluation Dec. 10 [C313 Opp to classroom]. 930am100pm
 Prepare a 10 minute presentation containing mostly your work done for the project including novelty. Presentation should clearly describe your contributions. A maximum of 10 slides is only permitted for a single person project or 15 slides for two person project. Slides should be sent by email by Dec. 10th morning 8am.
 A two page two column report on the work done for the project should be submitted by Dec. 9th latest by 4pm. Students are encouraged to use the overleaf template of ICML. link
Syllabus
 Introduction to real world signals  text, speech, image, video.
 Feature extraction and frontend signal processing  information rich representations, robustness to noise and artifacts.
 Basics of pattern recognition, Generative modeling  Gaussian and mixture Gaussian models.
 Discriminative modeling  support vector machines, neural networks and back propagation.
 Introduction to deep learning  convolutional and recurrent networks, attention in neural networks, pretraining and practical considerations in deep learning, understanding deep networks.
 Deep generative models  Autoencoders, Boltzmann machines, Adverserial Networks, Variational Learning.
 Applications in NLP, computer vision and speech recognition.
Grading Details
Assignments  15% 
Midterm exam.  20% 
Final exam.  35% 
Project  30% 
Prerequisites
 Must  Random Process/Probablity and Statistics
 Must  Linear Algebra/Matrix Theory
 Preferred  Basic Digital Signal Processing/Signals and Systems
Textbooks
 “Pattern Recognition and Machine Learning”, C.M. Bishop, 2nd Edition, Springer, 2011.
 “Neural Networks”, C.M. Bishop, Oxford Press, 1995.
 “Deep Learning”, I. Goodfellow, Y, Bengio, A. Courville, MIT Press, 2016. html
References
 “Deep Learning : Methods and Applications”, Li Deng, Microsoft Technical Report.
 “Automatic Speech Recognition  Deep learning approach”  D. Yu, L. Deng, Springer, 2014.
 “Machine Learning for Audio, Image and Video Analysis”, F. Camastra, Vinciarelli, Springer, 2007. pdf
 Various Published Papers and Online Material
 Python Programming Basics pdf
Slides
05082019  Introduction to real world signals  text, speech, image, video. Learning as a pattern recognition problem. Examples. Roadmap of the course. 
slides  
12082019  Basics of Natural Language Processing  token, document and corpus. TFIDF features. Language modeling. Smoothing and backoff. Introduction to audio signal processing. Discrete Fourier Transform, Short Term Fourier Transform. Information Extraction Book (Chapter 6)  TFIDF Stanford Reading Material  Language Modeling 
Weblink Weblink slides 

19082019  Shortterm Fourier Transform considerations. Melfrequency cepstral coefficient (MFCC) features. Image processing  filtering, convolutions. Matrix derivatives. Dimensionality Reduction  Principal Component Analysis Columbia Univ. STFT Tutorial PRML  Bishop (Appendix C) 
Weblink slides 

21082019  Unsupervised dimensionality reduction using Principal Component Analysis. Maximum variance formulation. Solution using eigenvectors of data covariance matrix. Minimum error formulation. Whitening and standardization. PRML  Bishop (Chapter 12.1) PRML  Bishop (Chapter 4.1.4) 
slides 

26082019  PCA for high dimensional data. Supervised dimensionality reduction using linear discriminant analysis (LDA). Fisher discriminant. Solution for 2 class LDA. Multiclass LDA. Comparison between PCA and LDA. PRML  Bishop (Chapter 4.1.4) PRML  Bishop (Chapter 1.5) 
slides 

28082019  Introduction to basics of decision theory. Inference and decision problems. Prior, likelihood and posterior. Maximumaposteriori decision rule for two class example. Decision theory for regression. MMSE estimation. Multivariate Gaussian Modeling. Intrepretation of Covariance. Diagonal and Full Covariance. Maximum Likelihood estimation of mean and covariance.
PRML  Bishop (Chapter 1.6) Further Reading 
slides 

04042019  Shortcomings of single Gaussian modeling. Introduction to mixture Gaussian modeling. Properties and parameters. Expectation Maximization algorithm  auxillary Function, proof of conververgence. Ref  Tutorial on GMMs Proof of EM algorithm 
slides 

09092019  Expectation Maximization Algorithm for GMMs. Initiatialization using Kmeans. Other Considerations in GMMs. GMM example for unsupervised clustering. Ref  EM algorithm for GMMs 
slides 

11092019  Assignment #1. Due on 23092019. Analytical part submitted in class. Coding part submitted via mlsp19.iisc aT gmail doT com. 
HW2 
Audio 
Text 
11092019  GMM Intialization. Other Considerations in GMMs. Factor Analysis. EM Algorithm for Factor Analysis. Applications. 
slides 

16092019  Nonnegative Matrix Factorization. Model formulation. Learning the parameters. Applications in audio source separation. Ref  Lee Paper on NMFs Ref  Audio Applications For NMF 
slides 

23092019  Linear Regression revisited. Maximum likelihood formulation and equivalence to least squares error. Regularized least squares PRML  Bishop (Chapter 3) 
slides 

25092019  MidTerm #1.


27092019  Decomposition of total loss into bias, variance and noise. Bias variance tradeoff in Regularized linear regression. Linear models for classification. PRML  Bishop (Chapter 3,4) 

30092019  Probablistic Linear Models for Classification  Logistic Regression. Motivation and formulation for 2class case and Kclass case. Comparison with linear models for classification. Regularized least squares revisited  Primal and dual form. Optimization in the dual space. Introduction kernel function and Gram matrix. PRML  Bishop (Chapter 4,6) 
slides  
02102019  Assignment #3. Due on 14102019. Analytical part submitted in class. Coding part submitted via mlsp19.iisc aT gmail doT com. 
HW3 
Image 
Text 
02102019  Properties of kernel functions. Rules for constructing kernels. The RBF kernel. Maximum margin classifiers  problem formulation for linearly separable case. Optimization fundamentals  primal and dual problems, strong duality, KKT conditions. PRML  Bishop (Chapter 6, 7) Introduction to convex optimization  Boyd (Chapter 5) 
Weblink to the book 

09102019  Maximum margin classifiers (nonoverlapping condition), primal and dual. Definition of support vectors. Complimentary slackness and KKT conditions for SVM PRML  Bishop (Chapter 7) 
slides  
14102019  Maximum margin classifiers (Overlapping condition), slack variables KKT conditions. Applications of SVMs. Support Vector Regression. PRML  Bishop (Chapter 7) 
slides  
16102019  Introduction to artificial neural networks  extension of kernel machines. Perceptron model. Multilayer perceptron. Activation Functions. Inputoutput Mapping. NNPR  Bishop (Chapter 3,4) 
slides 

18102019  Forward pass in MLP. Backpropagation algorithm  recursion. Choice of hidden layer activation function. NNPR  Bishop (Chapter 4) 

21102019  Cross entropy for two class. Expected cross entropy loss and posterior probability estimation. General condition on error function for outputs to be posterior probability. Weight learning  gradient descent method. Properties of gradient descent using quadratic approximation. Learning rate parameter. NNPR  Bishop (Chapter 6,7) 

23102019  Computational complexity in Gradient Descent. Definition of Jacobian and Hessian matrices. Choice of error function. Mean square and conditional expectation. Accelerating Gradient Descent Method, Momentum, Adagrad and Adam Optimizers. NNPR  Bishop (Chapter 6) Overview of Learning Algorithms 
slides 

25102019  Assignment #4. Analytical part submitted in class and codes submitted via mlsp19.iisc aT gmail doT com (04112019).. 
HW4 

28102019  Biasvariance tradeoff in neural networks. Improving generalization in deep learning. Regularization  weight decay, dropout strategy, training with noise. Early stopping. Committee of Neural networks. NNPR  Bishop (Chapter 9) 
slides 

30102019  Introduction to deep learning. Depth versus Width. Intuition behind deep representation learning. Folding analogy of deep learning. Convolutional operations in deep neural networks.
number of linear regions 
slides 

04112019  Convolutional Neural Networks, Computation of convolutions. Number of parameters. Advantages over deep neural networks. Pooling and subsampling. Backpropagation in convolution. Introduction to recurrence operations in modeling sequence data. Deep Learning Book  Goodfellow et al. (Chapter 9) 
slides 

06112019  Recurrent Neural Networks. Backprogation in time. Problem of vanishing gradients. Long short term memory networks. Various RNN architectures and applications. Deep Learning Book  Goodfellow et al. (Chapter 10) 
slides 

06112019  Assignment #5. Analysis of coding part submitted as report in class. Codes submitted separately via mlsp19.iisc aT gmail doT com (due date of 20112019). 
HW5 

08112019  Understanding and Visualizing Neural Network Activations. Stochastic Neighborhood Embedding and tdistributed Stochastic Neighborhood Embedding (tSNE). Visualizing activations in image networks and audio networks. tSNE paper 
slides 

11112019  Deep generative modeling  Restricted Boltzmann Machines (RBMs). Conditional independence property. RBM parameter learning. Positive and negative phase of learning. Intuitions behind contrastive divergence algorithm Deep Learning Book  Goodfellow et al. (Chapter 18,19,20) 
slides 

13112019  Autoencoders (AE). Variational autoencoders. Variational lower bound derivation. KL divergence derivation. Data generation with VAEs. Kingma's paper link VAE Tutorial link 
slides 

18112019  Generative Adversarial Networks. Intuition and Model Description. Theoretical bounds on the goals of GANs. GANs for data generation. Deep learning models for text. Word2vec model. GAN paper 
slides 

20112019  Deep learning for speech. Speech recognition models. Endtoend speech modeling. Deep learning for computer vision. Image classification and segmentation. Summary of the Course.  slides 

25112019  Practice Exam for Finals.

practiceTest 