Deep Neural Networks (DNNs) have been widely used in various artificial intelligence (AI)
applications due to their overwhelming performance. Furthermore, recently, several …

A scalable deep-learning accelerator supporting the training process is implemented for
device personalization of deep convolutional neural networks (CNNs). It consists of three …

The out-of-distribution (OOD) problem generally arises when neural networks encounter
data that significantly deviates from the training data distribution, ie, in-distribution (InD). In …

Training deep neural networks (DNNs) on edge devices has attracted increasing attention in
real-world applications for domain adaption and privacy protection. However, deploying …

With the prospering of mobile devices, the distributed learning approach, enabling model
training with decentralized data, has attracted great interest from researchers. However, the …

In deep neural network (DNN) training, network weights are iteratively updated with the
weight gradients that are obtained from stochastic gradient descent (SGD). Since SGD …

Deep neural network (DNN) training is an iterative process of updating network weights,
called gradient computation, where (mini-batch) stochastic gradient descent (SGD) …

As deep learning applications often encounter accuracy degradation due to the distorted
inputs from a variety of environmental conditions, training with personal data has become …

Deep neural networks (DNNs) are widely used in many artificial intelligence applications;
many specialized DNN-inference accelerators have been proposed. However, existing DNN …

Machine/deep-learning (ML/DL) based techniques are emerging as a driving force behind
many cutting-edge technologies, achieving high accuracy on computer vision workloads …