Information extraction, e.g., attribute value extraction, has been
exten...
Automatic Speech Recognition models require large amount of speech data ...
Understanding product attributes plays an important role in improving on...
Due to the over-parameterization nature, neural networks are a powerful ...
The inductive bias of a neural network is largely determined by the
arch...
Recent work on minimum hyperspherical energy (MHE) has demonstrated its
...
Neural networks are a powerful class of nonlinear functions that can be
...
In this paper we propose novel Deformable Part Networks (DPNs) to learn ...
Inner product-based convolution has been a central component of convolut...
We propose a robust elastic net (REN) model for high-dimensional sparse
...