A novel neural network model is described that implements context-dependent learning of complex sequences. The model utilises leaky integrate-and-fire neurons to extract timing inf...
This paper presents our solution for KDD Cup 2008 competition that aims at optimizing the area under ROC for breast cancer detection. We exploited weighted-based classification me...
Abstract--An audio fingerprint is a compact yet very robust representation of the perceptually relevant parts of an audio signal. It can be used for content-based audio identificat...
This work presents an experimental evaluation of different features for use in speaker identification. The features are tested using speech data provided by the CHAINS corpus, in a...
Abstract--We present an algorithm that coevolves fitness predictors, optimized for the solution population, which reduce fitness evaluation cost and frequency, while maintaining ev...