Reservoir Computing (RC) techniques use a fixed (usually randomly created) recurrent neural network, or more generally any dynamic system, which operates at the edge of stability,...
Eric A. Antonelo, Benjamin Schrauwen, Dirk Strooba...
This paper presents a new development of the NeuroVaria method. NeuroVaria computes relevant atmospheric and oceanic parameters by minimizing the difference between the observed s...
—In this paper, a neural network solution to extract independent components from nonlinearly mixed signals is proposed. Firstly, a structurally constrained mixing model is introd...
Pei Gao, Li Chin Khor, Wai Lok Woo, Satnam Singh D...
This project describes the electricity demand and energy consumption management system and its application to Southern Peru smelter. It is composted of an hourly demand-forecastin...
This article focusses on the problems of feature extraction and the recognition of handwritten digits. A trainable feature extractor based on the LeNet5 convolutional neural netwo...