Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Voinea, Stephen"'
The complexity of a learning task is increased by transformations in the input space that preserve class identity. Visual object recognition for example is affected by changes in viewpoint, scale, illumination or planar transformations. While drastic
Externí odkaz:
http://arxiv.org/abs/1703.04775
We analyze in this paper a random feature map based on a theory of invariance I-theory introduced recently. More specifically, a group invariant signal signature is obtained through cumulative distributions of group transformed random projections. Ou
Externí odkaz:
http://arxiv.org/abs/1506.02544
Recognition of speech, and in particular the ability to generalize and learn from small sets of labelled examples like humans do, depends on an appropriate representation of the acoustic input. We formulate the problem of finding robust speech featur
Externí odkaz:
http://arxiv.org/abs/1406.3884
Representations in the auditory cortex might be based on mechanisms similar to the visual ventral stream; modules for building invariance to transformations and multiple layers for compositionality and selectivity. In this paper we propose the use of
Externí odkaz:
http://arxiv.org/abs/1404.0400
In batch learning, stability together with existence and uniqueness of the solution corresponds to well-posedness of Empirical Risk Minimization (ERM) methods; recently, it was proved that CV_loo stability is necessary and sufficient for generalizati
Externí odkaz:
http://arxiv.org/abs/1105.4701
Publikováno v:
arXiv
ICASSP
ICASSP
Representations in the auditory cortex might be based on mechanisms similar to the visual ventral stream; modules for building invariance to transformations and multiple layers for compositionality and selectivity. In this paper we propose the use of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c39d9abf5f5bd19243cbc0d9b19059db