Deep Learning has enabled many advances in machine learning applications in the last few
years. However, since current Deep Learning algorithms require much energy for …

ImageNet-1K serves as the primary dataset for pretraining deep learning models for
computer vision tasks. ImageNet-21K dataset, which is bigger and more diverse, is used …

Target encoding plays a central role when learning Convolutional Neural Networks. In this
realm, one-hot encoding is the most prevalent strategy due to its simplicity. However, this so …

In recent years, larger and deeper models are springing up and continuously pushing state-
of-the-art (SOTA) results across various fields like natural language processing (NLP) and …

This paper introduces a structured memory which can be easily integrated into a neural
network. The memory is very large by design and significantly increases the capacity of the …

Training neural network language models over large vocabularies is still computationally
very costly compared to count-based models such as Kneser-Ney. At the same time, neural …

Extreme multi-label classification (XMLC) is a problem of tagging an instance with a small
subset of relevant labels chosen from an extremely large pool of possible labels. Large label …

Memory networks are neural networks with an explicit memory component that can be both
read and written to by the network. The memory is often addressed in a soft way using a …

The computational cost of training with softmax cross entropy loss grows linearly with the
number of classes. For the settings where a large number of classes are involved, a …

Factorized models, such as two tower neural network models, are widely used for scoring
(query, document) pairs in information retrieval tasks. These models are typically trained by …