24 citations · 26 across the 3 of their papers we have counts for
3 papers
Discriminate-and-Rectify Encoders: Learning from Image Transformation Sets
Andrea Tacchetti, Stephen Voinea, Georgios Evangelopoulos
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 v…
Learning An Invariant Speech Representation
Georgios Evangelopoulos, Stephen Voinea, Chiyuan Zhang +2
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 ac…
A Deep Representation for Invariance And Music Classification
Chiyuan Zhang, Georgios Evangelopoulos, Stephen Voinea +2
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…