Out-of-distribution (OOD) inputs can compromise the performance and safe...
While current deep learning algorithms have been successful for a wide
v...
In this article, we propose a novel form of unsupervised learning, conti...
We propose a fully Bayesian framework for learning ground truth labels f...
For lossy image compression, we develop a neural-based system which lear...
Hand-crafting effective and efficient structures for recurrent neural
ne...
Neuro-evolution and neural architecture search algorithms have gained
in...
We propose novel neural temporal models for short-term motion prediction...
The theory of situated cognition postulates that language is inseparable...
Finding biologically plausible alternatives to back-propagation of error...
For lossy image compression systems, we develop an algorithm called iter...
The use of back-propagation and its variants to train deep networks is o...