Winter course on Machine Intelligence and Brain Research

By Prof Sukhendu Das, Prof. Jaikishan Jayakumar, Prof. Partha Mitra | IIT Madras

Learners enrolled: 909

Contemporary AI is based on Artificial Neural Network models inspired by real biological neuronal networks. This course, which can be thought of as “neuroscience for an engineering/technology audience”, is cross-disciplinary and runs in two parallel but correlated tracks, covering neurobiology as well as machine learning. The course was previously offered in-person as the winter course on Machine Intelligence and Brain Research at the Center for Computational Brain Research, IIT Madras. What you will learn? At the end of the course, the student is expected to gain familiarity with both biological and artificial neural networks, in the context of vision, speech/language and reinforcement learning. This will include hands-on guided tutorials, conducted in small groups by zoom, to deepen the understanding of the material. Students will also be introduced to current research on mapping brain circuits. More information can be found here at the Center for Computational Brain Research website here.

INTENDED AUDIENCE: UG/PG students interested in the interface between Brain Science and Machine Intelligence

PRE-REQUISITE : Third year undergraduate and above

INDUSTRY SUPPORT : Companies and Industries dealing with AI and artificial neural networks; neuroscience research departments

Course Structure

Part I: (Weeks 1 -3) (Weeks starting 20th September 2021- 8th October 2021)

Self guided tutorals and Assessment (due Oct 7th 2021). This assessment forms a hurdle to help us guage your suitability to proceed to part II.

Part II (Weeks 2-12) (Weeks starting 11the October 2021- 9th December 2021)

Monday: Lectures on the topic of the week made available (can be watched at the learners convinience)
Thursday (6pm- 8 pm IST)- Live interactive tutorials in small groups headed by a TA via zoom rooms
Thursday (9:30 pm IST) or alternatively Friday (9:30 am IST)- Q and A with lecturers, course developers and international experts
Friday: Reflective quiz on the topic with due date on the following Monday.

**Please note that attendance for these live tutorials is compulsory

Summary

Course Status :	Ongoing
Course Type :	Core
Language for course content :	English
Duration :	Self Paced
Category :	Multidisciplinary
Credit Points :	3
Level :	Undergraduate/Postgraduate

Page Visits

Course layout

The course is divided into two parts: Part 1 (3 weeks) is a self guided tutorial to familiarize yourself with Google colab, Python and fundamental neuroscience.
Part 2( weeks 4-12) consists of lectures, live tutorials on specific topics.

Week 1 (starting September 20, 2021): Introduction to Google colab and Python notebooks

Week 2 (starting September 27, 2021 ): Introductory topics in Machine Learning and Neuroscience

Week 3 (starting October 4th 2021): Review and hurdle assessment

Week 4 (starting October 11th 2021) : Neuro track: Neurobiology of vision Tutorials on October 14th 2021

Week 5 (starting October 18th 2021) : ML track: Machine Vision Tutorials on October 21, 2021

Week 6 (starting October 25th 2021): ML track: Fundamentals of Machine Learning Tutorials on October 28, 2021

Week 7 (starting November 1, 2021) : Neuro track: Neurobiology of audition Tutorials on Novermber 4th, 2021

Week 8 (starting November 8, 2021): ML track: Speech signal processing and speech recognition Tutorials on November 11, 2021

Week 9 (starting November 15, 2021): ML track: Natural language processing Tutorials on Novermber 18th 2021

Week 10 (starting November 22, 2021): ML track: Reinforcement learning Tutorials on Novermber 25th 2021

Week 11 (starting November 27 2021): Neuro track: Modern neuroanatomy 1: Circuits Tutorials on December 2, 2021

Week 12 (starting December 6th 2021): Neuro track: Modern neuroanatomy 2: Cell types Tutorials on December 9, 2021

Books and references

Reference Books:

Deep Learning; Ian Goodfellow and Yoshua Bengio and Aaron Courville, An MIT Press book, 2016.
Computer Vision: Algorithms and Applications; Richard Szeliski, Springer- Verlag London Limited, 2011.
Reinforcement Learning: An Introduction; R. S. Sutton and A. G. Barto, MIT Press, 1st Edn., 1998.
Neuroscience; Dale Purves; [5th Edition], Sinauer Associates, Inc., USA, 2012.
Speech and Language Processing; Daniel Jurafsky, James H. Martin; Prentice Hall Series in Artificial Intelligence; 2nd Edn., 2013.
ISL - An Introduction to Statistical Learning with Applications in R; Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani. Springer. 2013 (7th printing 2017).
Computational Neuroscience of Vision; by Edmund Rolls, Gustavo Deco; Oxford University Press, 1st edition, 2002.
Brain Architecture – Understanding the basic plan; Larry Swanson, Oxford University Press, 2nd Edn., 2012.

Instructor bio

Prof Sukhendu Das

IIT Madras

Prof Sukhendu Das is a professor at the Department of Computer Science and Engineering at the Indian Institute of Technology Madras (IIT Madras) with interests in Visual Perception, Computer Vision, Image Intelligence, Graphics and Visualization, Biometry, Computational Science and Engineering, Analog and Digital Systems and Soft Computing.

Prof. Jaikishan Jayakumar

Dr Jaikishan Jayakumar is a Senior Project Advisor at the Center for Computational Brain Research, IIT Madras. My current research interests are in the organization of neural circuits, visual neuroscience, and behavioral neuroscience.

Prof. Partha Mitra

Prof Partha Mitra is a professor at the Cold Spring Harbor Laboratory in New York, USA and the HN Mahabala distinguished chair of Computational Brain Research at IIT Madras. His interests are in understanding intelligent machines using tools that are the interface between physics, engineering and biology, bringing methods from statistical physics to bear on questions about the workings of complex biological networks.