In this theoretical contribution we provide mathematical proof that two of the most important classes of network learning - correlation-based differential Hebbian learning and rew...
Christoph Kolodziejski, Bernd Porr, Minija Tamosiu...
Abstract. We show that some language theoretic and logical characterizations of recognizable word languages whose syntactic monoid is in the variety DA also hold over traces. To th...
Human action video sequences can be considered as nonlinear dynamic shape manifolds in the space of image frames. In this paper, we address learning and classifying human actions ...
Context-aware sensing is an integral part of the Body Sensor Network (BSN) design and it allows the understanding of intrinsic characteristics of the sensed signal and determinati...
Surapa Thiemjarus, Benny P. L. Lo, Guang-Zhong Yan...
Abstract— Supervised learning rules for spiking neural networks are currently only able to use time-to-first-spike coding and are plagued by very irregular learning curves due t...