SHF: Small: Energy and Computational Efficient Deep Generative AI Models via Emerging Devices, Circuits, and Architectures

SHF：小型：通过新兴设备、电路和架构实现能源和计算高效的深度生成人工智能模型

基本信息

批准号：
2219753
负责人：
Qilian Liang
金额：
$ 59.92万
依托单位：
University of Texas at Arlington
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2022
资助国家：
美国
起止时间：
2022-07-15 至 2025-06-30
项目状态：
未结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=2219753&HistoricalAwards=false
关键词：
SHF Small Energy Computational Efficient

项目摘要

Deep generative artificial intelligence (AI) models can learn to reproduce their inputs or the variational versions of their inputs. However, a critical challenge that needs to be addressed is their energy and computational cost. Foundational research in the design, verification, operation, and evaluation of deep generative AI hardware and software through novel approaches in emerging devices, circuits, and architectures is desirable. The energy and computational cost of AI has become a bottleneck for its applications in the real world. Research and education will be integrated through course and lab development. Under-represented and women students will be recruited for this project through the Society of Hispanic Professional Engineers, National Society of Black Engineers, and Society of Woman Engineers.This project targets the development of new generative AI models with simpler designs and architecture than are currently available. A novel path is explored for designing deep-learning hardware accelerators via efforts that span from devices and circuits to architectures and algorithms. The Cellular Neural Network-based realizations for key operations in convolution-based networks is studied, because it allows the bulk of the computation associated with a deep generative AI model to be performed in the analog domain. The development of mixed-signal circuits and architectures that lead to the best deep generative network designs by exploiting unique physics of emerging device technologies is investigated. The project is expected to generate orders of magnitude improvements in energy and delay for deep generative AI models, which will promote their applications and benefit the AI industry.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

深层生成人工智能（AI）模型可以学会复制其输入或输入的变异版本。但是，需要解决的关键挑战是它们的能量和计算成本。希望通过新兴设备，电路和体系结构中的新方法对设计，验证，操作和评估进行设计，验证，操作和评估。人工智能的能量和计算成本已成为其在现实世界中应用的瓶颈。研究和教育将通过课程和实验室发展整合。将通过西班牙裔专业工程师，国家黑人工程师和女工程师协会的社会为该项目招募人数不足和女学生。该项目的旨在开发具有比目前可用的新生成AI模型的新生成AI模型。探索了一条新颖的道路，可以通过从设备和电路到体系结构和算法的努力来设计深入学习的硬件加速器。研究了基于基于卷积的网络中的关键操作的基于细胞神经网络的实现，因为它允许在模拟域中执行与深层生成AI模型相关的大部分计算。研究了通过利用新兴设备技术的独特物理学来开发的混合信号电路和体系结构，从而导致最佳的深层生成网络设计。预计该项目将在深层生成AI模型的能源和延迟方面提高数量级，这将促进其应用并受益于AI行业。该奖项反映了NSF的法定任务，并认为值得通过基金会的知识分子评估来支持支持，并具有更广泛的影响。

项目成果

期刊论文数量（7）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

5G Channel Forecasting and Power Allocation Based on LSTM Network and Cooperative Communication

基于LSTM网络和协作通信的5G信道预测和功率分配

DOI：
发表时间：
2022
期刊：
Lecture notes of the Institute for Computer Sciences Social Informatics and Telecommunications Engineering
影响因子：
0
作者：
Zhangliang Chen, Qilian Liang
通讯作者：
Zhangliang Chen, Qilian Liang

A statistical approach for neural network pruning with application to internet of things

DOI：
10.1186/s13638-023-02254-3
发表时间：
2023-05
期刊：
EURASIP Journal on Wireless Communications and Networking
影响因子：
2.6
作者：
Chengchen Mao;Q. Liang;C. Pan;Ioannis Schizas
通讯作者：
Chengchen Mao;Q. Liang;C. Pan;Ioannis Schizas

Neural Network for UWB Radar Sensor Network-Based Sense-Through-Wall Human Detection

用于基于 UWB 雷达传感器网络的穿墙人体检测的神经网络

DOI：
发表时间：
2023
期刊：
Lecture notes in electrical engineering
影响因子：
0
作者：
Dheeral Bhole, Qilian Liang
通讯作者：
Dheeral Bhole, Qilian Liang

Towards Area Efficient Logic Circuit: Exploring Potential of Reconfigurable Gate by Generic Exact Synthesis

迈向面积高效的逻辑电路：通过通用精确综合探索可重构门的潜力

DOI：
10.1109/ojcs.2023.3247752
发表时间：
2023
期刊：
IEEE Open Journal of the Computer Society
影响因子：
5.9
作者：
Shang, Liuting;Naeemi, Azad;Pan, Chenyun
通讯作者：
Pan, Chenyun

Graphene-Based Interconnect Exploration for Large SRAM Caches for Ultrascaled Technology Nodes

DOI：
10.1109/ted.2022.3225512
发表时间：
2023-01
期刊：
IEEE Transactions on Electron Devices
影响因子：
3.1
作者：
Zhenlin Pei;M. Mayahinia;Hsiao-Hsuan Liu;M. Tahoori;F. Catthoor;Z. Tokei;C. Pan
通讯作者：
Zhenlin Pei;M. Mayahinia;Hsiao-Hsuan Liu;M. Tahoori;F. Catthoor;Z. Tokei;C. Pan