Related papers: Revisiting DNN Training for Intermittently-Powered…

Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of…

Deep neural networks (DNNs) have achieved unprecedented success in the field of artificial intelligence (AI), including computer vision, natural language processing and speech recognition. However, their superior performance comes at the…

Since the emergence of Deep Neural Networks (DNNs) as a prominent technique in the field of computer vision, the ImageNet classification challenge has played a major role in advancing the state-of-the-art. While accuracy figures have…

Learn in-situ is a growing trend for Edge AI. Training deep neural network (DNN) on edge devices is challenging because both energy and memory are constrained. Low precision training helps to reduce the energy cost of a single training…

Unlike existing work in deep neural network (DNN) graphs optimization for inference performance, we explore DNN graph optimization for energy awareness and savings for power- and resource-constrained machine learning devices. We present a…

Recently there has been significant research on power generation, distribution and transmission efficiency especially in the case of renewable resources. The main objective is reduction of energy losses and this requires improvements on…

Deep learning has experienced significant growth in recent years, resulting in increased energy consumption and carbon emission from the use of GPUs for training deep neural networks (DNNs). Answering the call for sustainability,…

Federated learning (FL) necessitates that edge devices conduct local training and communicate with a parameter server, resulting in significant energy consumption. A key challenge in practical FL systems is the rapid depletion of…

When dealing with deep neural network (DNN) applications on edge devices, continuously updating the model is important. Although updating a model with real incoming data is ideal, using all of them is not always feasible due to limits, such…

Deep neural networks (DNNs) are state-of-the-art solutions for many machine learning applications, and have been widely used on mobile devices. Running DNNs on resource-constrained mobile devices often requires the help from edge servers…

Dropout and DropConnect are well-known techniques that apply a consistent drop rate to randomly deactivate neurons or edges in a neural network layer during training. This paper introduces a novel methodology that assigns dynamic drop rates…

The paper presents a novel, principled approach to train recurrent neural networks from the Reservoir Computing family that are robust to missing part of the input features at prediction time. By building on the ensembling properties of…

We introduce Dynamic Dropout, a novel regularization technique designed to enhance the training efficiency of Transformer models by dynamically adjusting the dropout rate based on training epochs or validation loss improvements. This…

Deep neural networks (DNNs) have been successfully applied in various fields. A major challenge of deploying DNNs, especially on edge devices, is power consumption, due to the large number of multiply-and-accumulate (MAC) operations. To…

Recent breakthroughs in Deep Learning (DL) applications have made DL models a key component in almost every modern computing system. The increased popularity of DL applications deployed on a wide-spectrum of platforms have resulted in a…

There has been a growing interest in developing data-driven, and in particular deep neural network (DNN) based methods for modern communication tasks. For a few popular tasks such as power control, beamforming, and MIMO detection, these…

Deep Neural Network (DNN) has gained unprecedented performance due to its automated feature extraction capability. This high order performance leads to significant incorporation of DNN models in different Internet of Things (IoT)…

This paper presents a dynamic network rewiring (DNR) method to generate pruned deep neural network (DNN) models that are robust against adversarial attacks yet maintain high accuracy on clean images. In particular, the disclosed DNR method…

Deep neural networks (DNNs) are becoming increasingly deeper, wider, and non-linear due to the growing demands on prediction accuracy and analysis quality. When training a DNN model, the intermediate activation data must be saved in the…

Low harvested energy poses a significant challenge to sustaining continuous communication in energy harvesting (EH)-powered wireless sensor networks. This is mainly due to intermittent and limited power availability from radio frequency…