We propose a committee-based active learning method for large vocabulary continuous speech recognition. In this approach, multiple recognizers are prepared beforehand, and the rec...
The collection of multiple genome-scale datasets is now routine, and the frontier of research in systems biology has shifted accordingly. Rather than clustering a single dataset t...
Balaji S. Srinivasan, Nigam H. Shah, Jason Flannic...
Hidden Markov Models (HMMs) are one of the most fundamental and widely used statistical tools for modeling discrete time series. In general, learning HMMs from data is computation...
Component based development is a promising approach for embedded systems. Typical for embedded software is the presence of resource constraints in multiple dimensions. An essentia...
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...