中文
相关论文

相关论文: Auto-NBA: Efficient and Effective Search Over the …

200 篇论文

Multiplication is arguably the most cost-dominant operation in modern deep neural networks (DNNs), limiting their achievable efficiency and thus more extensive deployment in resource-constrained applications. To tackle this limitation,…

硬件体系结构 · 计算机科学 2022-12-20 Huihong Shi , Haoran You , Yang Zhao , Zhongfeng Wang , Yingyan Lin

Powerful yet complex deep neural networks (DNNs) have fueled a booming demand for efficient DNN solutions to bring DNN-powered intelligence into numerous applications. Jointly optimizing the networks and their accelerators are promising in…

机器学习 · 计算机科学 2025-01-07 Yongan Zhang , Yonggan Fu , Weiwen Jiang , Chaojian Li , Haoran You , Meng Li , Vikas Chandra , Yingyan Celine Lin

Neural architectures and hardware accelerators have been two driving forces for the progress in deep learning. Previous works typically attempt to optimize hardware given a fixed model architecture or model architecture given fixed…

Current neural architecture search (NAS) algorithms still require expert knowledge and effort to design a search space for network construction. In this paper, we consider automating the search space design to minimize human interference,…

计算机视觉与模式识别 · 计算机科学 2021-03-23 Daquan Zhou , Xiaojie Jin , Xiaochen Lian , Linjie Yang , Yujing Xue , Qibin Hou , Jiashi Feng

The significant computational cost of multiplications hinders the deployment of deep neural networks (DNNs) on edge devices. While multiplication-free models offer enhanced hardware efficiency, they typically sacrifice accuracy. As a…

机器学习 · 计算机科学 2024-09-10 Yang Xu , Huihong Shi , Zhongfeng Wang

High quality AI solutions require joint optimization of AI algorithms, such as deep neural networks (DNNs), and their hardware accelerators. To improve the overall solution quality as well as to boost the design productivity, efficient…

硬件体系结构 · 计算机科学 2020-10-16 Cong Hao , Yao Chen , Xiaofan Zhang , Yuhong Li , Jinjun Xiong , Wen-mei Hwu , Deming Chen

The rapidly evolving field of Artificial Intelligence necessitates automated approaches to co-design neural network architecture and neural accelerators to maximize system efficiency and address productivity challenges. To enable joint…

In view of the performance limitations of fully-decoupled designs for neural architectures and accelerators, hardware-software co-design has been emerging to fully reap the benefits of flexible design spaces and optimize neural network…

硬件体系结构 · 计算机科学 2022-03-29 Bingqian Lu , Zheyu Yan , Yiyu Shi , Shaolei Ren

Binary Neural Networks (BNNs) have gained extensive attention for their superior inferencing efficiency and compression ratio compared to traditional full-precision networks. However, due to the unique characteristics of BNNs, designing a…

计算机视觉与模式识别 · 计算机科学 2024-08-29 Zhihao Lin , Yongtao Wang , Jinhe Zhang , Xiaojie Chu , Haibin Ling

Co-exploration of an optimal neural architecture and its hardware accelerator is an approach of rising interest which addresses the computational cost problem, especially in low-profile systems. The large co-exploration space is often…

机器学习 · 计算机科学 2023-01-24 Deokki Hong , Kanghyun Choi , Hye Yoon Lee , Joonsang Yu , Noseong Park , Youngsok Kim , Jinho Lee

As we advance in the fast-growing era of Machine Learning, various new and more complex neural architectures are arising to tackle problem more efficiently. On the one hand their efficient usage requires advanced knowledge and expertise,…

机器学习 · 计算机科学 2023-10-30 Léo Pouy , Fouad Khenfri , Patrick Leserf , Chokri Mraidha , Cherif Larouci

Deep Neural Networks (DNNs) have the potential for making various clinical procedures more time-efficient by automating medical image segmentation. Due to their strong, in some cases human-level, performance, they have become the standard…

图像与视频处理 · 电气工程与系统科学 2022-02-24 Martijn M. A. Bosma , Arkadiy Dushatskiy , Monika Grewal , Tanja Alderliesten , Peter A. N. Bosman

Neural architecture search (NAS) can have a significant impact in computer vision by automatically designing optimal neural network architectures for various tasks. A variant, binarized neural architecture search (BNAS), with a search space…

计算机视觉与模式识别 · 计算机科学 2020-02-12 Hanlin Chen , Li'an Zhuo , Baochang Zhang , Xiawu Zheng , Jianzhuang Liu , David Doermann , Rongrong Ji

The use of deep learning has grown at an exponential rate, giving rise to numerous specialized hardware and software systems for deep learning. Because the design space of deep learning software stacks and hardware accelerators is diverse…

机器学习 · 计算机科学 2020-10-06 Zhan Shi , Chirag Sakhuja , Milad Hashemi , Kevin Swersky , Calvin Lin

In this paper, we present a novel technique to search for hardware architectures of accelerators optimized for end-to-end training of deep neural networks (DNNs). Our approach addresses both single-device and distributed pipeline and tensor…

硬件体系结构 · 计算机科学 2024-04-24 Muhammad Adnan , Amar Phanishayee , Janardhan Kulkarni , Prashant J. Nair , Divya Mahajan

Neural architecture search (NAS) has been very successful at outperforming human-designed convolutional neural networks (CNN) in accuracy, and when hardware information is present, latency as well. However, NAS-designed CNNs typically have…

信号处理 · 电气工程与系统科学 2020-03-09 Mohamed S. Abdelfattah , Łukasz Dudziak , Thomas Chau , Royson Lee , Hyeji Kim , Nicholas D. Lane

Graph neural networks (GNN) has been successfully applied to operate on the graph-structured data. Given a specific scenario, rich human expertise and tremendous laborious trials are usually required to identify a suitable GNN architecture.…

机器学习 · 计算机科学 2019-09-11 Kaixiong Zhou , Qingquan Song , Xiao Huang , Xia Hu

To cope with the ever-increasing computational demand of the DNN execution, recent neural architecture search (NAS) algorithms consider hardware cost metrics into account, such as GPU latency. To further pursue a fast, efficient execution,…

机器学习 · 计算机科学 2021-02-17 Kanghyun Choi , Deokki Hong , Hojae Yoon , Joonsang Yu , Youngsok Kim , Jinho Lee

While existing work on neural architecture search (NAS) tunes hyperparameters in a separate post-processing step, we demonstrate that architectural choices and other hyperparameter settings interact in a way that can render this separation…

机器学习 · 计算机科学 2018-07-19 Arber Zela , Aaron Klein , Stefan Falkner , Frank Hutter

Deep neural networks (DNNs) have been shown to outperform conventional machine learning algorithms across a wide range of applications, e.g., image recognition, object detection, robotics, and natural language processing. However, the high…

分布式、并行与集群计算 · 计算机科学 2020-04-23 Ye Yu , Yingmin Li , Shuai Che , Niraj K. Jha , Weifeng Zhang
‹ 上一页 1 2 3 10 下一页 ›