EventSession Formset ID 278

Event: ccnw23 2023
Type: Discussion
Title: Options for single-pass and single-shot learning mechanisms
is_program_session: True
Description:

 

As well as being a notable feature of biological learning mechanisms and therefore worthy of study in its own right, single-shot and single-pass learning offers many advantages including (potentially huge) gains in speed and energy use, as well as continuous and adaptive learning.  I would like to explore the options primarily in the context of - but not limited to - neuromorphic hardware and neurally-inspired learning and inference algorithms.

It may be useful to describe relevant aspects of the recently published BitBrain algorithm as one example.

Speaker:
Moderators: Michael Hopkins,
Schedule ID start time end time location
338 May 02 2023, 14:00 May 02 2023, 15:00 Sala panorama
389 May 08 2023, 16:00 May 08 2023, 17:00 Lecture room
372 May 05 2023, 14:00 May 05 2023, 15:00 Lecture room
List all sessions Update Delete