Join us (submit papers to) for the *Brains and Bits: Neuroscience Meets Machine Learning* *NIPS Workshop: 9 & 10 December 2016 Barcelona, Spain* http://www.stat.ucla.edu/~akfletcher/brainsbits.html The goal of this workshop is to bring together researchers in deep learning, machine learning, statistics, and computational neuroscience, and facilitate discussion about a) shared approaches for analyzing biological and artificial neural systems, b) how insights and challenges from neuroscience can inspire progress in machine learning, and c) machine learning methods for interpreting the revolutionary large scale datasets produced by new experimental neuroscience techniques. We invite high-quality submissions of abstracts for posters and contributed talks though CMT. Instructions are below. OverviewExperimental methods for measuring neural activity and structure have undergone recent revolutionary advances, including in high-density recording arrays, population calcium imaging, and large-scale reconstructions of anatomical circuitry. These developments promise unprecedented insights into the collective dynamics of neural populations and thereby the underpinnings of brain-like computation. However, these next-generation methods for measuring the brain’s architecture and function produce high-dimensional, large scale, and complex datasets, raising challenges for analysis. What are the machine learning and analysis approaches that will be indispensable for analyzing these next-generation datasets? What are the computational bottlenecks and challenges that must be overcome? In parallel to experimental progress in neuroscience, the rise of deep learning methods has shown that hard computational problems can be solved by machine learning algorithms that are inspired by biological neural networks, and built by cascading many nonlinear units. In contrast to the brain, artificial neural systems are fully observable, so that experimental data-collection constraints are not relevant. Nevertheless, it has proven challenging to develop a theoretical understanding of how neural networks solve tasks, and what features are critical to their performance. Thus, while deep networks differ from biological neural networks in many ways, they provide an interesting testing ground for evaluating strategies for understanding neural processing systems. Are there synergies between analysis methods for biological and artificial neural systems? Has the resurgence of deep learning resulted in new hypotheses or strategies for trying to understand biological neural networks? Conversely, can neuroscience provide inspiration for the next generation of machine-learning algorithms? We welcome participants from a range of disciplines in statistics, applied physics, machine learning, and both theoretical and experimental neuroscience, with the goal of fostering interdisciplinary insights. We hope that active discussions among these groups can set in motion new collaborations and facilitate future breakthroughs on fundamental research problems. ------------------------------ Organizers - Eva Dyer <http://kordinglab.com/people/eva_dyer/> Northwestern University - Allie Fletcher <http://www.stat.ucla.edu/~akfletcher/> Statistics, UCLA & UCB Redwood Center for Neuroscience - Konrad Kording <http://koerding.com//> Rehabilitation Institute of Chicago, Northwestern University - Jascha Sohl-Dickstein <http://www.sohldickstein.com/> Google Research - Joshua Vogelstein <http://jovo.me/> Biomedical Engineering, Johns Hopkins University - Jakob Macke <http://www.mackelab.org/> caesar Bonn, an Institute of the Max Planck Society Current Speakers - Christos Papadimitriou <https://people.eecs.berkeley.edu/~christos/> EECS, UC Berkeley - Adrienne Fairhall <https://fairhalllab.com/> Psychology and Biophysics, University of Washington - Yoshua Bengio <http://www.iro.umontreal.ca/~bengioy/yoshua_en/index.html> Computer Science and Operations Research, Université de Montréal - Sophie Denève <http://iec-lnc.ens.fr/group-for-neural-theory/members/faculty-in-alphabetical-order/deneve-sophie/> Group for Neural Theory, LNC, DEC, ENS - Demis Hassabis <http://demishassabis.com/> Google DeepMind - Terry Sejnowski <http://www.salk.edu/scientist/terrence-sejnowski/> Howard Hughes Medical Institute and Salk Institute, UCSD - Mitya Chklovskii <https://www.simonsfoundation.org/simons-center-for-data-analysis/scda-neuroscience-group/> Simons Foundation - Anima Anandkumar <http://newport.eecs.uci.edu/anandkumar/> EECS, UC Irvine - David Cox <http://www.coxlab.org/> Molecular and Cellular Biology and Computer Science, Harvard University - Surya Ganguli <https://web.stanford.edu/dept/app-physics/cgi-bin/person/surya-gangulijanuary-2012/> Applied Physics, Stanford University - Maneesh Sahani <http://www.gatsby.ucl.ac.uk/~maneesh/> Gatsby Institute, University College, London - Emily Fox <https://www.stat.washington.edu/~ebfox/> Statistics and Computer Science, University of Washington - Jonathan Pillow <http://pillowlab.princeton.edu/> Center for Statistics and Machine Learning, Princeton University - Fred Hamprecht <https://hciweb.iwr.uni-heidelberg.de/people/fhamprec> Heidelberg Collaboratory for Image Processing (HCI), Heidelberg - Max Welling, University of Amsterdam Submission Information & Important Dates Submissions will be considered both for poster and oral presentation. See instructions on the workshop website at http://www.stat.ucla.edu/~ akfletcher/brainsbits.html Submission deadline: 29 September 2016 11:59 PM PDT (UTC -7 hours) Acceptance notification: 12 October 2016