Recently, over-parameterized deep networks, with increasingly more network parameters
than training samples, have dominated the performances of modern machine learning …

Abstract Spiking Neural Networks (SNNs) have recently emerged as a new generation of
low-power deep neural networks, which is suitable to be implemented on low-power …

This paper studies the curious phenomenon for machine learning models with Transformer
architectures that their activation maps are sparse. By activation map we refer to the …

In the realm of deep learning-based recommendation systems, the increasing computational
demands, driven by the growing number of users and items, pose a significant challenge to …

Sparse neural networks are a key factor in developing resource-efficient machine learning
applications. We propose the novel and powerful sparse learning method Adaptive …

This article does not propose any novel algorithm or new hardware for sparsity. Instead, it
aims to serve the" common good" for the increasingly prosperous Sparse Neural Network …

The rapid development of large-scale deep learning models questions the affordability of
hardware platforms, which necessitates the pruning to reduce their computational and …

Although increasing model size can enhance the adversarial robustness of deep neural
networks, in resource-constrained environments, there exist critical sparsity constraints …

Tomorrow's robots will need to distinguish useful information from noise when performing
different tasks. A household robot for instance may continuously receive a plethora of …

Deep neural networks (DNNs) in the wireless communication domain have been shown to
be hardly generalizable to scenarios where the train and test datasets follow a different …