Search

link to homepage

Institute for Advanced Simulation (IAS)

Navigation and service


IAS Seminar "From ConvNets to cortex: an engineering perspective"

begin
23 Nov 2016 15:00
end
23 Nov 2016 16:00
venue
Jülich Supercomputing Centre, Rotunda, building 16.4, room 301
Speaker:
James Knight, Advanced Processor Technologies Research Group, University
of Manchester, UK
Abstract:
Convolutional neural networks (ConvNets) are inspired by the organization of the mammalian visual cortex and are currently the best performing solution to a large range of problems ranging from speech synthesis to image classification. In this talk, I will first compare the structure of ConvNets to that of the type of more realistic cortical models employed by theoretical neuroscientists. I will then discuss how the structures of these models affect efficiency when running them on different computer architectures: whereas GPUs are well suited to both training and performing inference using ConvNets, supercomputers or specialized neuromorphic hardware are currently the best means of running large-scale models of the cortex.
In the final section of this talk, I will discuss recent developments in bringing these two classes of models closer together. These developments include transferring ConvNets trained on GPUs to neuromorphic hardware – allowing inference to be performed at low power using spiking neurons.
Date:
Wednesday, 23 November 2016, 15:00
Venue:
Jülich Supercomputing Centre, Rotunda, building 16.4, room 301
Announcement as pdf file:
 From ConvNets to cortex: an engineering perspective (PDF, 28 kB)

Anyone interested is cordially invited to participate in this seminar.
Contact: Dr. Jenia Jitsev, j.jitsev@fz-juelich.de


Servicemeu

Homepage