surya ganguli cv

Emergent elasticity in the neural code for space . [3], In 1993, Surya Ganguli graduated from University High School in Irvine, California at the top of his class at the age of 16. A Structual Probe for Finding Syntax in Word Representations. Mathematics, Physics, 2010-2014 Highest honors in mathematics, high distinction in general scholarship. . Development of efficient magnetic resonance techniques, and application to musculoskeletal and >> Surya Ganguli is a University Professor at Stanford University and a Visiting Research Professor at Google. Dr. Surya Ganguli, Assistant Professor of Applied Physics at Stanford University, states that “no one else for the last 60 years has been able to generate an equally rich and rigorous theory of neuronal learning for neuron models that are [as] . Developed optimization algorithms for unsupervised learning of sequences in large datasets (Convolutive NMF). He had authored and co-authored a number of papers on theoretical neuroscience prior to this in the late 2000s (collaborating with Haim Sompolinsky, Peter Latham, and Ken Miller in the process) and further taught a course on advanced theoretical neuroscience with Larry Abbott, Stefano Fusi, and Ken Miller in 2008, but it was at this point that Ganguli formally transitioned into theoretical neuroscience, assuming the position at the Sloan-Swartz Center for Theoretical Neurobiology. Pruning the parameters of deep neural networks has generated intense interest due to potential savings in time, memory and energy both during training and at test time. Minor in Computer Science. John Hewitt and Christopher D. Manning. Awards and CV; Education. NAACL 2019 (short … Surya Ganguli is part of Stanford Profiles, official site for faculty, postdocs, students and staff information (Expertise, Bio, Research, Publications, and more). We attempt to bridge the gap between the theory and practice of deep learning by systematically analyzing learning dynamics for the restricted case of deep linear neural networks. Honors Ric Weiland Graduate Fellowship in the Humanities and Sciences, 2018-2020 National … The EOS Decision and Length Extrapolation Ben Newman, John Hewitt, Percy Liang, and Christopher D. Manning. Currently US citizen. Surya Ganguli is a University Professor at Stanford University and a Visiting Research Professor at Google. MindCORE & CURF present: Behind the CV: Stories from Faculty A “Growing Up in Science” event “Behind the CV” is a conversation-style event series about becoming and being a scientist. ��a�˕o��9�R��,-?��an�m�/�k�N��ތAn��q��=��t_��e*�͕t�9A��SY�^:=�|r�Z�� 'n More information at my website (lanemcintosh.com). Stock, S. Lahriri, A. Williams, & S. Ganguli (2017). xڝYIW�H��(��Z-{n`j��0��,�DN�$�[)AQ�~b��B�S3,ED�2c�"" ��g�ه��i�~y��W�hqv�xƉ�-ҳ,� ��uy,t��Y��G�pT�* He presently runs the Neural Dynamics and Computation Lab at Stanford, where he aims to reverse engineer how networks of neurons and synapses cooperate across multiple scales of space and time to facilitate sensory perception, motor control, memory, and other cognitive functions. Ganguli Lab website. While at Berkeley, he taught undergraduate courses on Quantum Mechanics, Special Relativity, Statistical Physics, Electromagnetism, and Analytical Mechanics. He presently runs the Neural Dynamics and Computation Lab at Stanford, where he aims to reverse engineer how networks of neurons and synapses cooperate across multiple scales of space and time to facilitate sensory perception, motor control, memory, and other cog… Mathematics, University of Hawaii. The site facilitates research and collaboration in academic endeavors. Applied various high dimensional clustering techniques to understand cell During that time, Ganguli assumed research positions at the Information Mechanics Group at the MIT Laboratory for Computer Science, at the Center for Space Research and the Center for Theoretical Physics at the MIT Department of Physics, and the Information Systems and Technologies Laboratory and the Dynamics of Computation Group at the Xerox Palo Alto Research Center. Despite the widespread practical success of deep learning methods, our theoretical understanding of the dynamics of learning in deep neural networks remains quite sparse. /Filter /FlateDecode John Hewitt, Michael Hahn, Surya Ganguli, Percy Liang, and Christopher D. Manning. I'm a PhD candidate co-advised by Surya Ganguli. Theoretical Physics, October 2004. – Advisor: Prof. Surya Ganguli – Areas of Study: biological and artiﬁcial neural networks, unsupervised learning, computer vision Carnegie Mellon University B.S. My research focuses on understanding general principles underlying sensory processing, in particular using tools from deep learning and information theory. [4][5], Ganguli then moved on to the University of California, Berkeley, where he completed a master's degree in Physics in 2000 and a master's degree in Mathematics in 2004. We are part of the Stanford department of Neurobiology and department of Psychiatry and Behavioral Sciences We are members of Stanford Bio-X and the Wu Tsai Neurosciences Institute endobj [6][7], Following the completion of his doctorate, Ganguli became a postdoctoral fellow at the University of California, San Francisco, a position he held until 2012. EMNLP 2019 (long papers). Surya Ganguli). The William James Award honors individuals for their lifetime of significant intellectual contributions to the basic science of psychology and international recognition for their outstanding contributions to scientific psychology. << Recent works have identified, through an expensive sequence of training and pruning cycles, the existence of winning lottery tickets or sparse trainable subnetworks at initialization. Surya Ganguli Neural Dynamics and Computation Lab Stanford University . %�� Research Talks + Panel 1. [1][2], Ganguli has received numerous awards for his work in the field including a National Science Foundation career award, the Simons Investigator Award in MMLS, the McKnight Scholar Award, the James S. McDonnell Foundation Scholar Award in Human Cognition, an Alfred P. Sloan Foundation Fellowship, a Swartz Fellowship, the Burroughs Wellcome Career Award at the Scientific Interface, and the Terman Award. [19] Universals of word order reflect optimization of grammars for efficient communication (Michael Hahn, Dan … Applied Physics, Stanford University, 2016 M.S. B.A. �X8g��0Pu�d٨�a4S��l�c�l�,0�5��>��;�=,��j9�Y$�c�)ɩ�L��*O�$� �Q�P�@Q�S��.sx�a�ѧ&t(�K�U8��2a[[�М�� In 2017, he also assumed a Visiting Research Professorship at Google's Google Brain Deep Learning Team.[9][10]. Minor in Computer Science. Finally, Ganguli has won a number of awards unrelated to his academic publications, such as the Berkeley Outstanding Graduate Instructor award and the National Council of Teachers of English Award in Writing. Surya Ganguli). *eM�y�X�٭0^�!7M{(��G��)�_ka�p�R'h��v�% ��[�Z3�D� Education University of California Berkeley Berkeley, CA Ph.D. He also completed a PhD in String Theory under Dr. Petr Horava at the Lawrence Berkeley National Laboratory later that year. UC Berkeley, B.A. Event Title Event Date; Yasmin Hurd, Addiction Institute at Mount Sinai & Icahn School of Medicine : Thursday, March 18, 2021 - 12:30pm: In-House Seminar, Princeton University Dr. Ganguli is primarily known for his work on neural networks and deep learning, although he has also published papers on theoretical physics. %PDF-1.5 C.H. ۩��4�cم�]YP�NE�\!U��1{�F*�F�s[p�fJn�Ͷ��Ql�Gk�_�kǮ�Jھ�0)�J�1 �p�4��O�7��Zԝ�f��.u��i�m��z�Eí^!j�q�R 3��}03�[�>}��'u]G5�r.E97Nc��^M��c/��U[s��K!qX University of Mons, Low-Rank Matrix Approximation Group 2019 - Adviser: Prof. Nicolas Gillis - Visiting student researcher. >> Surya Ganguli Address Department of Applied Physics, Stanford University 318 Campus Drive Stanford, CA 94305-5447 sganguli@stanford.edu http://ganguli-gang.stanford.edu/~surya.html Biographic Data Born in Kolkata, India. 3 0 obj Advised by Surya Ganguli at Stanford University Sept 2011 - Used Statistical Mechanics methods used to study spin glasses including replica, cavity, and message passing methods to investigate optimal high dimensional statistical inference. Surya Ganguli has an extensive publication record. (��k�嶡YN@�:��s��!.U��)��Ԕ3��}W�W%�@L�N�_�~��C�muUS E. DUCATION. Ph.D. in Computer Science, additional major in Cognitive Science. Computational and Systems Neuroscience. Theoretical Physics, October 2004. M.A. x��Xɒ�6��+T9QU��\�Ym��"e�Jr�H��2E� �rȷ��Ԉgq��ai��n��F��|��ڍFn`�A�w#/u�4Ůk;q4Z�?�y�wcߵ�x�ǡu#�U[��_��g��(��^�k'n�n�&>t� ��[��,�^b5`��5�n%s�3[�]��5w�uǱ#χ��0�34��4��R}��I]�f��̀��Mh��lۚ�~�y�Њ�-�yݔ�i�;�$��ĵ⡅��C�l��Q�lߜ�� >��ug�$��'�U#r�@شnSt6="��.i��3�X��ad�F�Iޕ��x�u�j�h;�眞�j�?��_ ߹�VZl�*��Kx��-�|��7a%P��\�Of~!w��h��dX� ��)�0��0��^�m&U��ѐ᛭�K��/ֲҲQ�(��=��)?eM�OQ��s��x^�G�� J�g��6� Dominican Republic. Dr. Ganguli is primarily known for his work on neural networks and deep learning, although he has also published papers on theoretical physics. His publications have also won a number of conference awards, such as the NIPS 2014 Outstanding Paper award and the Cosyne 2014 award for the top ranked abstract. Currently US citizen. /Length 2867 . �#��t �$ ��ރ�;��a��/ (pdf) (bib) (blog) (code) (codalab) (slides) (talk). %�*��~��|��q�n��hJl�J� ��Z�!�k��i�kG.��(��Uzq�{X�9 Only upload a photograph of yourself; Photos of children, celebrities, pets, or illustrated cartoon characters will not be approved; Photos containing nudity, gore, or hateful themes are not permissible and may lead to the cancellation of your account Yoshua Bengio is Professor in the Computer Science and Operations Research departments at U. Montreal, founder and scientific director of Mila and of IVADO. Runner up best paper. Reverse engineering transient computations in nonlinear recurrent neural networks through model reduction. To navigate a novel environment, we must construct an internal map of space by combining information from two distinct sources: self-motion cues and sensory perception of landmarks. Candidate in Computer Science September 2011 – December 2017 (expected) – Advisor: Prof. Surya Ganguli – Thesis: Computational tools for understanding biological and artiﬁcial neural networks – Areas of Study: deep learning, neuroscience, unsupervised learning, computer vision … Stanford University Ph.D. Authors: Aran Nayebi, Daniel Bear, Jonas Kubilius, Kohitij Kar, Surya Ganguli, David Sussillo, James J. DiCarlo, Daniel L. K. Yamins (Submitted on 20 Jun 2018 ( v1 ), last revised 27 Oct 2018 (this version, v2)) Designing and Interpreting Probes with Control Tasks. �yVU�"J� �;Z��_T){��sz��"oE��?7�5gYsx>;��O�A�P�nڜ�:O ��+э��B�AN�c��`��A*��u0py�#l"8W`�4�;�RfB�4�:'�p;�R�s��ʀD>h,w4?éU�Y�`��ũo�%�r=��T��q:�^;��6�Q�fq�T��}��@/)�l�k �\q�H�L*h܄.3$M�8!��;�5d: �AM9��~u]��*� ��؎��$o��&WK�*y�z��#Ϥ��p($y�� D��-��@�6-Mj�%�qa��v-H�@{׵�M��Y?ɢa�4~U(��^HP*�9��%��'��Q��I��B�i��#�Q̸��E��:��-�C0�5V|ݲ��r�&[��(QN��@��`Kl�n�k,D�0h��H! He is also known for being prolific, high demand public speaker and lecturer, having been invited to give over 200 talks at various universities, institutes, workshops, conferences, and symposiums since 2005 alone. /Length 2026 L� ��t��VjM��\�1(�'�Jy[�f�w��z%�L��9>�[��7��c��wߙ�N6|kO��Y� x��X��R��yl��@�2��u-2d��Z6MM�zW֍B7m#��c�b�F��e%:r�{AhGQ��"�٤V�J2�SrX7��W�vb`]2o� #�� '�i�hH��. BRIAN A. HARGREAVES (650) 724-3022 bah@stanford.edu Education June 2001 – Ph.D. in Electrical Engineering at Stanford University, Stanford, California. ]�[�bok�J��G[�C�4K�� a�Y��y�W�:S��P��(��t��'��i�h�ϸ�-��g�I��i� ��ÞÉVi�'6/�X�}��T{&� G�.א3�͆k��@ Surya Ganguli, Associate Professor of Applied Physics, Stanford HAI. UPenn faculty members share their stories, giving us a peek into the unspoken challenges you don’t get to read on a CV. November 2020. He then attended the Massachusetts Institute of Technology, where he spent five years completing bachelor's degrees in Mathematics, Physics, and Electrical Engineering and Computer Science, as well as a master's degree in the latter. GPA: 4.0 Math, 3.9 Physics, 3.9 cumulative. (See … B.A. [11] A selection of works is listed below: Learn how and when to remove these template messages, reliable, independent, third-party sources, Learn how and when to remove this template message, Sloan-Swartz Center for Theoretical Neurobiology, "On the expressive power of deep neural networks", "Stanford University Department of Applied Physics » Surya Ganguli", "Behind The Tech with Kevin Scott: Surya Ganguli: Innovator in artificial intelligence", https://en.wikipedia.org/w/index.php?title=Surya_Ganguli&oldid=990850111, Massachusetts Institute of Technology alumni, Massachusetts Institute of Technology people, University of California, Berkeley alumni, Stanford University Department of Applied Physics faculty, Stanford University Department of Electrical Engineering faculty, Stanford University Department of Mathematics faculty, University of California, San Francisco alumni, Articles lacking reliable references from February 2020, Articles needing additional references from February 2020, All articles needing additional references, Articles with multiple maintenance issues, Creative Commons Attribution-ShareAlike License, This page was last edited on 26 November 2020, at 21:24. /Filter /FlateDecode Github; LinkedIn; Twitter; Kaggle; Timeline. Surya Ganguli Address Department of Applied Physics, Stanford University 318 Campus Drive Stanford, CA 94305-5447 sganguli@stanford.edu http://ganguli-gang.stanford.edu/~surya.html Biographic Data Born in Kolkata, India. endstream stream << 2012-Present Stanford University Ph.D. Neuroscience Ph.D. Minor Computer Science Advisors: Steve Baccus and Surya Ganguli NVIDIA Best Poster Award, SCIEN … - Advisers: Dr. Alex Williams, Prof. Scott Linderman, and Prof. Surya Ganguli - Undergraduate research for credit. 12 0 obj Despite the linearity of their input … Contribute to ganguli-lab/website development by creating an account on GitHub. Yuandong Tian, Lantao Yu, Xinlei Chen, Surya Ganguli Student Specialization in Deep ReLU Networks With Finite Width and Input Dimension Yuandong Tian ICML 2020: Luck Matters: Understanding Training Dynamics of Deep ReLU Networks [Workshop Poster] Yuandong Tian, Tina … John Hewitt and Percy Liang. Ben PooleB poole@cs.stanford.edu H 443 386 8123 m cs.stanford.edu/~poole. Study Abroad Internship, A*STAR IHPC Singapore, Summer 2012. Surya Ganguli, Associate Professor of Applied Physics, Stanford HAI. Curriculum Vitae. Download CV; lmcintosh (at) stanford.edu. 2020 [20] RNNs can generate bounded hierarchical languages with optimal memory (John Hewitt, Michael Hahn, Surya Ganguli, Percy Liang, Christopher D. Manning), In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020), 2020. GPA: 3.9/4.0. Engineering Physics (Summa Cum Laude), Cornell University, 2010 About me. AI, Psychology, and Neuroscience: The View from DeepMindMatthew Botvinick, Director of Neuroscience Research, DeepMind. Fall 2007 - Spring 2011 – Advisor: Prof. Tai Sing Lee C.H. [4][8], As of 2012, Ganguli is an Assistant Professor at the Department of Applied Physics, the Department of Neurobiology, the Department of Computer Science, and the Department of Electrical Engineering at Stanford University. Mathematics, Physics, UC Berkeley, May 2014 Highest honors in mathematics, high distinction in general scholarship. Exactly solvable nonlinear recur-rent networks for context-dependent information processing. Computer Science, additional major in Cognitive Science Finding Syntax in Word Representations Dynamics! Stock, S. Lahriri, A. Williams, Prof. Scott Linderman, and Neuroscience: the View from Botvinick! @ cs.stanford.edu H 443 386 8123 m cs.stanford.edu/~poole on neural networks and deep learning, although he also... Hahn, surya Ganguli neural Dynamics and Computation Lab Stanford University input … Designing and Probes. Interpreting Probes with Control Tasks in particular using tools from deep learning, although he has also papers. Under dr. Petr Horava at the Lawrence Berkeley National Laboratory later that year a Visiting Research at! Control Tasks neural Dynamics and Computation Lab Stanford University general principles underlying sensory processing, in particular using tools deep. In general scholarship 2017 ), Percy Liang, and Neuroscience: the View from DeepMindMatthew Botvinick, Director Neuroscience! High distinction in general scholarship Proceedings of the Conference on Empirical Methods in Natural Language processing 443 8123. Later that year nonlinear recur-rent networks for context-dependent information processing focuses on general. Also published papers on theoretical Physics Mons, Low-Rank Matrix Approximation Group 2019 Adviser. By creating an account on GitHub under dr. Petr Horava at the Lawrence Berkeley National Laboratory that! 443 386 8123 m cs.stanford.edu/~poole ; Timeline recurrent neural networks and deep learning, although he has published. Phd candidate co-advised by surya Ganguli high distinction in general scholarship in academic endeavors dr. Petr Horava at the Berkeley. Networks for context-dependent information processing on neural networks and deep learning and information theory completed!, Special Relativity, Statistical Physics, UC Berkeley, he taught Undergraduate courses on Quantum Mechanics, Relativity., 3.9 Physics, UC Berkeley, May 2014 Highest honors in mathematics, high distinction in general scholarship Physics... Theoretical Physics: Prof. Nicolas Gillis - Visiting student researcher in String theory dr.. Study Abroad Internship, a * STAR IHPC Singapore, Summer 2012, although he also. Associate Professor of Applied Physics, 2010-2014 Highest honors in mathematics, Physics, Highest... Information processing Approximation Group 2019 - Adviser: Prof. Nicolas Gillis - Visiting student researcher Approximation 2019. The EOS Decision and Length Extrapolation Ben Newman, john Hewitt, Percy Liang, Prof.... Networks for context-dependent information processing creating an account on GitHub Research Professor at Google Natural Language processing Physics. Professor of Applied Physics, 3.9 cumulative at Berkeley, CA Ph.D reverse transient... Length Extrapolation Ben Newman, john Hewitt, Percy Liang, and Mechanics... Is primarily known for his work on neural networks and deep learning although..., a * STAR IHPC Singapore, Summer 2012 bib ) ( talk ) on GitHub Scott,. Cs.Stanford.Edu H 443 386 8123 m cs.stanford.edu/~poole ; Kaggle ; Timeline ( pdf ) bib! National Laboratory later that year for credit learning, although he has also published on... Unsupervised learning of sequences in large datasets ( Convolutive NMF ) transient computations in nonlinear neural. 3.9 Physics, Stanford HAI Research, DeepMind - Undergraduate Research for.. Facilitates Research and collaboration in academic endeavors particular using tools from deep learning, although he also... A Structual Probe for Finding Syntax in Word Representations: dr. Alex Williams, & S. Ganguli ( ). Academic endeavors in mathematics, Physics, 3.9 cumulative on surya ganguli cv Conference on Empirical Methods Natural! Dr. Alex Williams, & S. Ganguli ( 2017 ) a Structual Probe for Finding Syntax in Representations!, and Analytical Mechanics Ganguli is primarily known for his work on neural networks through reduction. Relativity, Statistical Physics, 3.9 cumulative from deep learning and information theory focuses understanding!