We present a novel multi-layered unsupervised learning artifical immune system (MARIA). We have employed vector quantisation to augment MARIA (and Kohonen Networks) to allow for a ...
We present a new unsupervised learning technique for the discovery of temporal clusters in large data sets. Our method performs hierarchical decomposition of the data to find stru...
Newborns must learn to structure incoming acoustic information into segments, words, phrases, etc., before they can start to learn language. This process is thought to rely on mod...
Jonathan Le Roux, Hirokazu Kameoka, Nobutaka Ono, ...
Abstract. Seeking to identify the constituent parts of the multidimensional auditory attribute that musicians know as timbre, music psychologists have made extensive use of multidi...
Hsu et al. (2009) recently proposed an efficient, accurate spectral learning algorithm for Hidden Markov Models (HMMs). In this paper we relax their assumptions and prove a tighte...