Home

15th Neural Computation and Psychology Workshop

 August 8-9, 2016

Drexel University, Philadelphia, PA, USA

Contemporary Neural Network Models: 
Machine Learning, Artificial Intelligence, and Cognition

Funded by the W. K. & K. W. Estes Fund, Google DeepMind
and the Rumelhart Emergent Cognitive Functions Fund

 Organizers

Jay McClelland, Stefan Frank & Daniel Mirman

Invited Speakers

Nikolaus Kriegeskorte, Timothy Lillicrap, Andrew Saxe,
Linda Smith, Greg Wayne, & Marco Zorzi


 Overview

We are pleased to announce a workshop on Contemporary Neural Network Models, bringing the latest developments in Deep Neural Networks, Deep Reinforcement Learning Networks, and Recurrent Neural Networks with Long-Short-Term Memory Units into contact with contemporary cognitive science and cognitive neuroscience research.  Plenary speakers are established and emerging experts in the development of deep neural network models of perception, action and cognition, and include authors of Google DeepMind’s projects achieving human-level performance in Atari games and Go and in creating innovative Cognitive architectures such as the Neural Turing Machine. The workshop will continue the Neural Computation and Psychology Workshop (NCPW) series, which originated in the UK in 1992. It will take place on Aug 8-9, 2016 in Philadelphia – in North America for the first time after 14 previous meetings in Europe.

The Workshop has both a research dissemination and tutorial purpose. Research will be presented in any area of computational research that applies neural network models or related approaches to understanding human cognition.  To foster exchange of ideas, presentation of recently published work or work also submitted elsewhere is welcome, and there will be a publication option for new work.  Thanks to generous support, costs will be low and travel awards will encourage participation by a diverse population of participants with relevant goals. Participants will be invited to contribute otherwise unpublished work to a planned Frontiers in Cognitive Science Research Topic on contemporary neural network models. 

Workshop Structure

Each of the two days of NCPW will include three 75 minute sessions led by invited speakers. The first five of these sessions will each focus on a different aspect or topic in contemporary neural network research, and each will be led by a different expert.  The final session will begin with a commentary by a senior Cognitive Scientist (Linda Smith) followed by a panel discussion with the other five speakers.  During lunch each day, the day’s speakers will each hold a smaller discussion session with a subset of the workshop participants, and materials will be circulated in advance.   Two 1.5-hour sessions each day will be devoted to submitted presentations selected for their scientific value and the extent to which they advance the use of neural network architectures, tools, and concepts in both computational and cognitive (neuro)science domains.   A poster session at the end of the first day will allow all of the participants an opportunity to present and obtain feedback from the invited speakers, and to learn from and network with each other.  A conference dinner on the first evening and a reception on the second evening will allow for informal interactions.

See the workshop schedule page for further details.

NCPW15 will be complemented by a separate day-long tutorial workshop on Wednesday, August 10, as part of the Cognitive Science Society meeting also in Philadelphia. This day-long event will provide additional tutorial presentations, followed by in depth how-to sessions associated with the actual implementation and effective practical mastery of deep learning networks for cognitive science research.