— In connectionist learning, one relevant problem is “catastrophic forgetting” that may occur when a network, trained with a large set of patterns, has to learn new input pat...
Dario Albesano, Roberto Gemello, Pietro Laface, Fr...
Recently, a reconfigurable and biologically inspired paradigm based on network-on-chip (NoC) and spiking neural networks (SNNs) has been proposed as a new method of realising an ef...
Snaider Carrillo, Jim Harkin, Liam McDaid, Sandeep...
This paper presents a method that combines Mutual Information and k-Nearest Neighbors approximator for time series prediction. Mutual Information is used for input selection. K-Nea...
The research work is carried out to enhance the recognition accuracy of neural network with Phase Only Correlation (POC) and reduce the time required for POC by refining its input...
Many machine learning algorithms can be formulated as the minimization of a training criterion which involves (1) \training errors" on each training example and (2) some hype...