Results 21 to 30 of about 7,279,238 (253)
Sensors, 2021 With the development of deep learning technologies and edge computing, the combination of them can make artificial intelligence ubiquitous. Due to the constrained computation resources of the edge device, the research in the field of on-device deep ...
Zhao Yang +6 more
doaj +1 more source
, 2023 The fast growth of machine learning has brought us to a new era that characterizes two primary trends: design automation and hardware optimization.
Qing Lu (28914)
core +1 more source
Neural Architecture Search Survey: A Hardware Perspective [PDF]
, 2022 We review the problem of automating hardware-aware architectural design process of Deep Neural Networks (DNNs). The field of Convolutional Neural Network (CNN) algorithm design has led to advancements in many fields, such as computer vision, virtual ...
Chitty-Venkata, Krishna Teja +1 more
core
Pareto Rank-Preserving Supernetwork for Hardware-Aware Neural Architecture Search
, 2023 In neural architecture search (NAS), training every sampled architecture is very time-consuming and should be avoided. Weight-sharing is a promising solution to speed up the evaluation process. However, training the supernetwork incurs many discrepancies between the actual ranking and the predicted one. Additionally, efficient deep-learning engineering
Hadjer Benmeziane +3 more
openaire +1 more source
ENOS: Energy-Aware Network Operator Search in Deep Neural Networks
IEEE Access, 2022 This work proposes a novel Energy-aware Network Operator Search (ENOS) approach to address the energy-accuracy trade-offs of a deep neural network (DNN) accelerator.
Shamma Nasrin +6 more
doaj +1 more source
Data-Driven and Physics-Informed Modeling Perspectives for Soft Manipulators: From SINDy to Hybrid Intelligence. [PDF]
Adv Sci (Weinh)This Perspective charts the modeling landscape for soft manipulators, spanning sparse system identification, neural dynamics, physics‐informed models and hybrid intelligence. We examine how physics, data, sensing, adaptation and control can assume complementary roles within this landscape, and provide a framework for selecting modeling approaches ...
Hui W, Wang Y, Zhang T, Chen Y, Pan M.
europepmc +2 more sources
HADAS: Hardware-Aware Dynamic Neural Architecture Search for Edge Performance Scaling
2023 Design, Automation & Test in Europe Conference & Exhibition (DATE), 2023 Dynamic neural networks (DyNNs) have become viable techniques to enable intelligence on resource-constrained edge devices while maintaining computational efficiency. In many cases, the implementation of DyNNs can be sub-optimal due to its underlying backbone architecture being developed at the design stage independent of both: (i) the dynamic computing
Bouzidi, Halima +4 more
openaire +4 more sources
, 2022 Neural architecture search (NAS) is an emerging paradigm to automate the design of top-performing deep neural networks (DNNs). Specifically, the increasing success of NAS is attributed to the reliable performance estimation of different architectures ...
Luo, Xiangzhong +5 more
core +1 more source
IEEE Access, 2021 CNN design and deployment on embedded edge-processing systems is an error-prone and effort-hungry process, that poses the need for accurate and effective automated assisting tools.
Paola Busia +4 more
doaj +1 more source
A hardware-aware neural architecture search algorithm for wearable robotics
, 2023 Hardware-aware neural architecture search (HW NAS), the process of automating the design of neural architectures taking into consideration hardware constraints, has already outperformed the best human designs on many tasks. However, it is known to be highly demanding in terms of hardware, thus limiting access to non-habitual neural network users.
Garavagno, Andrea Mattia +3 more
openaire +2 more sources