Training large deep neural network models is highly challenging due to t...
Graph convolutional networks (GCNs) are becoming increasingly popular as...
In training of modern large natural language processing (NLP) models, it...
Graph convolutional networks (GCNs) are becoming increasingly popular as...
Co-exploration of an optimal neural architecture and its hardware accele...
Sequence alignment forms an important backbone in many sequencing
applic...
Recently, the application of advanced machine learning methods for asset...
The finance industry has adopted machine learning (ML) as a form of
quan...
Model quantization is considered as a promising method to greatly reduce...
Model quantization is known as a promising method to compress deep neura...
Attention mechanism has been regarded as an advanced technique to captur...
Data-free compression raises a new challenge because the original traini...
In this paper, we present GradPIM, a processing-in-memory architecture w...
In this study, we train deep neural networks to classify composer on a
s...
To cope with the ever-increasing computational demand of the DNN executi...
Binary Convolutional Neural Networks (BCNNs) can significantly improve t...
Generating an investment strategy using advanced deep learning methods i...
Knowing the similarity between sets of data has a number of positive
imp...
Target encoding is an effective technique to deliver better performance ...
We applied Deep Q-Network with a Convolutional Neural Network function
a...
Motivated by the need to extract knowledge and value from interconnected...
Tracking is one of the most important but still difficult tasks in compu...