Dear INSERT_FIRST_NAME INSERT_LAST_NAME
This email is sent on behalf of IEEE CS NMIT Chapter. Please find their invitation below:
-----------------------------------------------------------------------------------------------------------------
Dear INSERT_FIRST_NAME INSERT_LAST_NAME
Nitte Meenakshi Institute of Technology in association with IEEE Computer Society student branch is organizing a Webinar series on "Industry and Research Perspective on Data Science" to give a basic understanding of different technologies used in Data science for student and Technical professionals. The second talk is on 8 th June, 2020 at 7:00pm by Dr Snehanshu Saha
Speaker: Dr Snehanshu Saha
When: MONDAY, 8 JUNE 2020 | 7:00 PM to 8:00 PM IST
Registration Link: https://forms.gle/Gvn8EWo574NKGF4Q7
Limited Seats! | Registration is mandatory for receiving the webinar link | Registration closes at 09:00 AM IST on 8 JUNE 2020
About the topic: The talk aims to answer the age-old question of derivative-free optimization in neural networks. I'll introduce AdaSwarm, a novel derivative-free optimizer to have similar or better performance to Adam but without “gradients”. To support the AdaSwarm, a novel Particle Swarm Optimization method, Exponentially weighted Momentum PSO (EM-PSO), a derivative-free optimizer, is also proposed which tackles constrained and unconstrained single objective optimization problems and looks at applying the proposed momentum particle swarm optimization on benchmark test functions, engineering optimization problems and habitability scores for exoplanets which show speed and convergence of the technique. The EM-PSO is extended by approximating the gradient of a function at any point using the parameters of the particle swarm optimization. This is a novel technique to simulate gradient descent, an extremely popular method in the back-propagation algorithm, using the approximated gradients from the particle swarm optimization parameters. Mathematical proofs of gradient approximation by EM-PSO, thereby bypassing the gradient computation, will be discussed. The AdaSwarm is compared with various optimizers and the theory and algorithmic performance are supported by promising results.
About the speaker: Dr. Snehanshu Saha holds a Masters Degree in Mathematical and Computational Sciences at Clemson University and Ph.D. from the Department of Applied Mathematics at the University of Texas at Arlington in 2008. He was the recipient of the prestigious Dean's Fellowship during PhD. After working briefly at his Alma mater, Snehanshu moved to the University of Texas El Paso as a regular full time faculty in the Department of Mathematical Sciences. He is an Associate Professor of CS & IS and Anuradha and Prashanth Palakurthi Centre for Artificial Intelligence Research (APPCAIR), BITS PILANI K K Birla Goa Campus and heads the Center for AstroInformatics Modeling and Simulation (CAMS). He is also a visiting Professor at the department of Statistics, University of Georgia, USA. He has published 90 peer-reviewed articles in International journals and conferences. Dr. Saha is an IEEE Senior member, ACM Senior Member, Vice Chair-International Astrostatistics Association and Former Chair, IEEE Computer Society Bangalore Chapter. Dr. Saha is the Editor of Journal of Scientometric Research, a peer-reviewed SCI/SCOPUS indexed journal. He's an associate fellow of the Inter University Consortium of Astronomy & Astrophysics and a Fellow of IETE. Dr. Saha received the distinguished researcher award, PEACE in AstroInformatics and Machine Learning in 2019. Snehanshu’s current and future research interests lie in Data Science, Theory of Machine Learning and Astronomy.
---------------------------------------------------------------------------------------------------------------------------
For IEEE CS NMIT Chapter,
Thanks,
IEEE Computer Society Bangalore Chapter
