Course

You will find below material and schedule for Deep Learning: A Mathematical Introduction being discussed at TIFR-CAM, Bangalore, in the Fall of 2024. This will evolve as the discussion progress.

Syllabus & Schedule

Part-1: Deep Learning Models

Wk	Dt	Topics	Resources
01	07-Sep	1. Course Intro 2. FFNs	L01
02	tbd	1. CNNs Intro 2. Lab 3. Architectures	L02
03	21-Sep	1. KAN (with Splines) 2. Nonparametric Regression 2. KAN Variants	L03
04	24-Oct	1. RNNs 2. Lab	L04
05	16-Nov	1. Transformers 2. Lab	L05
06	14-Dec	1. State Space Models 2. Lab	L06

References

1. [course] CS6910, Prof. Mitesh Khapra’s CS6910 Deep Learning at IIT-M
2. [course] CS236 Prof. Stefano Emron’s course on Deep Generative Modeling at Stanford Fall’23
3. [Book] Deep Generative Modeling, Jakub Tomxzak
4. [Book] Understanding Deep Learning, Simon Prince
5. [Book] Deep Learning, Ian Goodfellow and Yoshua Bengio and Aaron Courville

References

• R01: CS6910: Deep Learning Prof. Mitesh Khapra @ IIT Madras
• R02: CS7015: Deep Learning Prof. Mitesh Khapra @ IIT Madras(earlier version of CS6910)
• R03: LING 574: Deep Learning for NLP Prof. Shane Steinert-Threlkeld @ University of Washington
• R04: Dive into Deep Learning Alex Smola et al
• R05: Understanding Deep Learning Prof. Simon Prince
• R06: Neural Networks and Deep Learning Michael Nielsen
• R07: Deep Learning for Computer Vision NPTEL course by Prof. Vineeth N Balasubramanian
• R08: CS236 Prof. Stefano Emron’s course on Deep Generative Modeling at Stanford Fall’23
• R09: Deep Generative Modeling, Jakub Tomxzak
• R10 Deep Learning, Ian Goodfellow and Yoshua Bengio and Aaron Courville

Soma S Dhavala
Discussion Anchor