In Vitro Philosophers: Chemical Reaction Networks that do Machine by Manoj Gopalkrishnan

438 views · Published 31 January 2018 · 36:09 · Indexed 14 November 2026

Channel: International Centre for Theoretical Sciences · 2018 · Science & Technology

Watch on YouTube

Statistical Physics Methods in Machine Learning

DATE:26 December 2017 to 30 December 2017
VENUE:Ramanujan Lecture Hall, ICTS, Bengaluru

The theme of this Discussion Meeting is the analysis of distributed/networked algorithms in machine learning and theoretical computer science in the "thermodynamic" limit of large number of variables. Methods from statistical physics (eg various mean-field approaches) simplify the performance analysis of these algorithms in the limit of many variables. In particular, phase-transition like phenomena appear where the performance can undergo a discontinuous change as an underlying parameter is continuously varied. A provocative question to be explored at the meeting is whether these methods can shed theoretical light into the workings of deep networks for machine learning.

The Discussion Meeting will aim to facilitate interaction between theoretical computer scientists, statistical physicists, machine learning researchers and mathematicians interested in these questions. Examples of specific topics to be covered include (but are not limited to) problems such as phase transitions in optimization and learning algorithms, matrix approximation, mixing in large networks, sub-linear time algorithms, learning theory and non convex optimization. The meeting will allow structured and and unstructured interactions among the participants around the main theme.

 
CONTACT US:spmml2017  ictsresin
PROGRAM LINK:https://www.icts.res.in/discussion-meeting/SPMML2017

Table of Contents (powered by https://videoken.com)
0:00:00 Start 
0:00:11 In vitro Philosophers: Chemical Reaction Networks that do Machine Learning
0:00:48 Neutrophil chasing a bacterium [David Rogers, Vanderbilt, 1950s]
0:02:31 Biochemical Reaction Networks
0:05:37 Synthetic analog computation in living cells
0:06:13 Chemical Reaction Network Designs for Asynchronous Logic Circuits
0:06:48 Computing with Reaction Networks
0:09:24 EXPECTATION MAXIMIZATION THE EM ALGORITHM
0:09:44 E(xponential)-projection
0:12:21 Mixture)-projection
0:13:30 Expectation Maximization (EM) Algorithm
0:14:37 In vitro E-projection
0:25:42 Expectation Maximization (EM) Algorithm
0:26:43 In vitro EM-algorithm
0:30:03 Cellular sensing as an EM problem
0:30:51 Conclusions and Future Work
0:34:15 References
0:35:34 Thermodynamics of computation references
0:35:49 Thank You

More from this channel