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.
|Tue, 02.05.2023||14:00 - 15:00||Sala panorama|
|Mon, 08.05.2023||16:00 - 17:00||Lecture room|
|Fri, 05.05.2023||14:00 - 15:00||Lecture room|