Our Information Bottleneck Theory of Deep Learning has recently been noticed – at last!
Recent & popular talks
ACDL, Siena, July 2019
MPI, Gottingen, July 2019
ISIT, Paris, July 2019
CBMM, Italy, June 2019
Gatsby triCenter meeting, London, June 2019
IPAM, Geometry of Big Data, UCLA, May 2019
Columbia University Economics, May 2019
IMVC, Tel-Aviv, April 2019
CERN, Geneva, ML for HEP, April 2019
BrainTech, Tel-Aviv, March 2019
ICERM, Brown University, February 2019
Deep Learning & the Brain, ELSC, Jerusalem, January 2019
Directions in Theoretical Physics, Edinburgh, January 2019
Statistical Physics and Machine Learning: A 30 Year Perspectives, APS Physics Next Workshop, October 2018
Part I of a Mini-Course on The Information Theory of Deep Learning, ICTP, Trieste, November 2018
Part II of a Mini-Course on The Information Theory of Deep Learning, ICTP, Trieste, November 2018
Part III of a Mini-Course on The Information Theory of Deep Learning, ICTP, Trieste, November 2018
“What Makes Us Human: From Genes to Machines”, June 6, 2018, Jerusalem.
A Talk at the Israel Academy of Science, June 6, 2018, Jerusalem
Interview on the future of Artificial Intelligence, The AI Summit, Berlin, June 2018.
Interview at SISSA , Trieste, Italy, before my physics colloquium, May 2018.
Perimeter Institute Physics Colloquium, Waterloo, Canada, April 2018.
Stanford CSE Colloquium, April 4, 2018.
Simons Institute, Berkeley, Public talk, April 9, 2018.
Simons Institute, Berkeley, “Brain & Computation program”, March 2018.
Human creativity, Music & Deep Learning, BIU, Nov. 29, 2017.
The Synergy between Information and Control
שבוע אמנות ומוח 2016 דוד גרוסמן ופרופ’ נפתלי תשבי בדיאלוג על מוח, מחשבה, דמיון ויצירה
My Current Lab:
- Gal Keynan
- Etam Benger
- Zoe Piran
- Shlomi Agmon
- Ravid Shwartz-Ziv
- Noga Zaslavsky
- Nadav Amir
- Ron Hecht(MSc 2007)
- Hadar Aharoni Levi
Selected Research Projects
We work at the interface between computer science, physics, and biology which provides some of the most challenging problems in today’s science and technology. We focus on organizing computational principles that govern information processing in biology, at all levels. To this end, we employ and develop methods that stem from statistical physics, information theory and computational learning theory, to analyze biological data and develop biologically inspired algorithms that can account for the observed performance of biological systems. We hope to find simple yet powerful computational mechanisms that may characterize evolved and adaptive systems, from the molecular level to the whole computational brain and interacting populations. An example is the Information Bottleneck method that provides a general principle for extracting relevant structure in multivariate data, characterizes complex processes, and suggests a general approach for understanding optimal adaptive biological behavior