In many computer vision tasks, scene changes hinder the generalization ability of trained classifiers. For instance, a human detector trained with one set of images is unlikely t...
Many activity dependent learning rules have been proposed in order to model long-term potentiation (LTP). Our aim is to derive a spike time dependent learning rule from a probabili...
Jean-Pascal Pfister, David Barber, Wulfram Gerstne...
We present a novel stereo vision modeling framework that generates approximate, yet physically-plausible representations of objects rather than creating accurate models that are c...
Krishnanand N. Kaipa, Josh C. Bongard, Andrew N. M...
Recruitment learning in hierarchies is an inherently unstable process (Valiant, 1994). This paper presents conditions on parameters for a feedforward network to ensure stable recru...
The general approach for automatically driving data collection using information from previously acquired data is called active learning. Traditional active learning addresses the...