zur Hauptseite

Institute for Advanced Simulation (IAS)

Navigation und Service

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

23.11.2016 15:00 Uhr
23.11.2016 16:00 Uhr
Jülich Supercomputing Centre, Rotunde, Geb. 16.4, R. 301

James Knight, Advanced Processor Technologies Research Group, University
of Manchester, UK
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.
Wednesday, 23 November 2016, 15:00
Jülich Supercomputing Centre, Rotunda, building 16.4, room 301
Ankündigung als pdf-Datei:
 From ConvNets to cortex: an engineering perspective (PDF, 28 kB)

Alle Interessierten sind herzlich eingeladen.
Ansprechpartner: Dr. Jenia Jitsev,