Abstract. In this paper, some sufficient conditions are obtained to guarantee that discrete time cellular neural networks (DTCNNs) can have some stable memory patterns. These condi...
Abstract. Robot recognition is a very important point for further improvements in game-play in RoboCup middle size league. In this paper we present a neural recognition method we d...
Ulrich Kaufmann, Gerd Mayer, Gerhard K. Kraetzschm...
Researchers have studied hybrid branch predictors that leverage the strengths of multiple stand-alone predictors. The common theme among the proposed techniques is a selection mec...
Abstract. We develop three new techniques to build on the recent advances in online learning with kernels. First, we show that an exponential speed-up in prediction time per trial ...
The well-known backpropagation (BP) derivative computation process for multilayer perceptrons (MLP) learning can be viewed as a simplified version of the Kelley-Bryson gradient f...