Learning of deep spiking networks

We will discuss possibilities of supervised training of deep spiking architectures. In the context of spiking networks back propagation is not applicable. Therefore, alternative approaches have to be followed. The goal of the group is to come up with different alternatives. One possible approach is recently proposed "target propagation", which employs local update rule that can be implemented with backward connection.

Login to become a member send

Timetable

Day	Time	Location
Tue, 26.04.2016	15:30 - 16:30	meet in the lobby
Thu, 28.04.2016	15:00 - 16:00	Panorama Room
Sat, 30.04.2016	14:00 - 15:00	Panorama Room

Difference Target Propagation (599.8 KB)

Leaders

Members