Abstract. This paper introduces an approximate fuzzy representation to FuzzyUCS, a Michigan-style Learning Fuzzy-Classifier System that evolves linguistic fuzzy rules, and studies ...
Albert Orriols-Puig, Jorge Casillas, Ester Bernad&...
This paper studies the problem of learning from ambiguous supervision, focusing on the task of learning semantic correspondences. A learning problem is said to be ambiguously supe...
Deep Belief Networks (DBNs) are hierarchical generative models which have been used successfully to model high dimensional visual data. However, they are not robust to common vari...
Sparse representation theory has been increasingly used in the fields of signal processing and machine learning. The standard sparse models are not invariant to spatial transform...
Data sparseness is an ever dominating problem in automatic emotion recognition. Using artificially generated speech for training or adapting models could potentially ease this: t...