NIPS Workshop on Representation Learning in Artificial and Biological Neural Networks (MLINI 2016) December 9th, 2016, Centre Convencions Internacional Barcelona, Barcelona, SPAIN *Call for papers and abstracts:* Submission deadline: *Tuesday, September 27th, 2016* Notification of acceptance: Wednesday, October 5th, 2016 Submission website: *https://cmt3.research.microsoft.com/MLINI2016 <https://cmt3.research.microsoft.com/MLINI2016>* Workshop Website: https://sites.google.com/site/mlini2016nips We invite submissions that are related, but not limited to: - Use of neural network and other methods as models of brain function - Machine learning methods, including deep learning, to analyze brain data - Cognitively plausible learning algorithms, or in general models that take insights from human brains or behavior We invite both: - Paper submissions, to be considered for online publication in arXiv proceedings, and poster presentation. The length should not exceed 6 pages in Springer format <http://www.springer.com/computer/lncs?SGWID=0-164-6-793341-0> (here are the LaTeX2e style files <ftp://ftp.springer.de/pub/tex/latex/llncs/latex2e/llncs2e.zip>), excluding the references. - Abstract submission, to be considered for poster presentation. The abstract should not exceed 500 words (figures are allowed). This workshop is in conjunction with a Frontiers topic entitled: Artificial neural networks as models of human brain function http://journal.frontiersin.org/researchtopic/4817/artificial -neural-networks-as-models-of-neural-information-processing Participants are strongly encouraged to submit their work to the Frontiers special topic edition (deadline is November 1st). *About the workshop:* This one day workshop is about the interface between cognitive neuroscience and recent advances in AI fields that aim to reproduce human performance, such as natural language processing or computer vision, and specifically the deep learning approaches in these disciplines. When studying the cognitive capabilities of the brain, scientists follow a system identification approach in which they present different stimuli to the subjects and try to model the evoked brain responses. The goal is to understand the brain by trying to find the function that expresses the activity of brain areas in terms of different properties of the stimulus. Experimental stimuli are becoming increasingly complex with more and more researchers studying real life phenomena such as the perception of natural images or natural sentences. There is therefore a need for rich and adequate representations of the properties of the stimulus, that can be obtained using advances in NLP, computer vision or other relevant ML disciplines. In parallel, many new ML approaches, especially in deep learning, are inspired to a certain extent by human behavior or biological principles. Neural networks for example were originally inspired by biological neurons. More recently, processes such as attention are being used which are inspired by human behavior. However, the large bulk of these methods are independent of findings about brain function, and it is unclear whether it is at all beneficial for machine learning to try to emulate brain function in order to achieve the same tasks that humans are capable of performing. In order to shed some light on this difficult but exciting question, we plan to bring together many experts from these seemingly converging fields to discuss these problems, in a new highly interactive format consisting of two short lectures from experts in both fields, followed by a guided discussion. This workshop is a continuation of the Machine Learning and Interpretation in Neuroimaging (MLINI) series. MLINI has already had 5 iterations in which methods for analyzing and interpreting neuroimaging data were discussed in depth. In keeping with tradition, we also invite contributions from the expanding field of machine learning applied to neuroimaging data, and specifically the recent trend of utilizing neural network models to analyze brain data, which is evolving in parallel to the use of these algorithms as models of the information content in the brain. This way we will complete the loop: we will explore how neural networks and other machine learning tools contribute to neuroscience, both as a source of models for brain representations, and as a tool for brain image analysis. *Organizers:* Guillermo Cecchi (IBM T.J. Watson Research Center) Moritz Grosse-Wentrup (Max Plank Institute for Intelligent Systems) Georg Langs (Medical University of Vienna, CSAIL, MIT) Brian Murphy (Queens University, Belfast) Anwar Nunez-Elizalde (Helen Wills Neuroscience Institute, University of California, Berkeley) Irina Rish (IBM T.J. Watson Research Center) Marcel van Gerven (Donders Institute for Brain, Cognition and Behaviour, Nijmegen) *Leila Wehbe (Helen Wills Neuroscience Institute, University of California, Berkeley) - main contact