Non-negative spectrogram factorization has been proposed for single-channel source separation tasks. These methods operate on the magnitude or power spectrogram of the input mixtur...
Separating machine printed text and handwriting from overlapping text is a challenging problem in the document analysis field and no reliable algorithms have been developed thus f...
Discovering a representation that allows auditory data to be parsimoniously represented is useful for many machine learning and signal processing tasks. Such a representation can ...
Reliable estimation of the classification performance of learned predictive models is difficult, when working in the small sample setting. When dealing with biological data it is ...
Antti Airola, Tapio Pahikkala, Willem Waegeman, Be...
We present a reinforcement learning architecture, Dyna-2, that encompasses both samplebased learning and sample-based search, and that generalises across states during both learni...