Machine Learning for Signal Processing - EE903 (eMasters)
Vipul Arora
Department of Electrical Engineering, IIT Kanpur
TAs
- Kavya Saxena (kavyars@iitk.ac.in)
- Raja Raviteja (rraja21@iitk.ac.in)
Course Objectives:
This course aims at introducing machine learning (ML) techniques used for various signal processing applications. There will be spectral processing methods for analysis and transformation of signals. The lectures will focus on mathematical principles, and there will be coding based assignments for implementation. Prior exposure to ML is not required. Intuitive understanding and illustrative examples will be provided for easy grasp of the principles.
Pre-requisites:
There are no official pre-requisites for the course. But you may brush up your knowledge of the basics of linear algebra and probability theory.
Topics:
- Digital Signal Processing basics
- Machine Learning basics
- Supervised Machine Learning
- Model Evaluation
- Linear Regression and Classification
- Neural Networks
- Programming Tools: Tensorflow and Keras
- Unsupervised Machine Learning
- Gaussian Mixture Models
- Some Applications in Signal Processing (time permitting)
Lecture wise topics
Week | Video in dropbox | Topics |
---|---|---|
1 | Lecture 1 | Signal Processing and Machine Learning |
1 | Lecture 2 | Time series, sampling and quantization, convolution, correlation |
2 | Lecture 3 | Periodic signals, Fourier Transforms |
2 | Lecture 4 | Spectral analysis, STFT |
2 | Lecture 5 | Representations and Feature extraction |
3 | Lecture 6 | ML introduction, geometrical understanding |
3 | Lecture 7 | ML evaluation |
3 | Lecture 8 | Data collection/annotation/extraction, model selection |
4 | Lecture 9 | Linear regression, Least square solution, ridge regression |
4 | Lecture 10 | Gradient descent, non-linear regression |
5 | Lecture 11 | Number of model parameters, error function |
5 | Lecture 12 | Back propagation algorithm |
6 | Lecture 13 | Linear classification, multi-class classification |
6 | Lecture 14 | Multi-class vs multi-label classification, Perceptron algo. |
7 | Lecture 15 | Neural Network Optimization |
7 | Lecture 16 | Convolutional Neural Networks - I |
8 | Lecture 17 | Convolutional Neural Networks - II |
8 | Lecture 18 | Recurrent Neural Networks |
References:
- “Pattern Recognition and Machine Learning”, C.M. Bishop, 2nd Edition, Springer, 2011.
- “Deep Learning”, I. Goodfellow, Y, Bengio, A. Courville, MIT Press, 2016.
- Tensorflow tutorials