CRII: SHF: Enabling Neuroevolution in Hardware
CRII: SHF: Enabling Neuroevolution in Hardware
批准号:
1755876
负责人:
Tushar Krishna
金额:
$17.5万
依托单位国家:
美国
项目类别:
Standard Grant
财政年份:
2018
资助国家:
美国
项目状态:
已结题
起止时间:
2018-01-15 至 2019-12-31
中文摘要
在过去的几年中,机器学习算法,特别是神经网络(NN)由于其在解决图像分类和语音识别等各种复杂问题方面的潜力而受到了广泛的欢迎。不幸的是,为了有效,神经网络需要有适当的拓扑(神经元之间的连接)来处理手头的任务,并且在连接上有正确的权重。这被称为监督学习,需要通过运行数tb到数pb的数据来训练神经网络。这种形式的机器学习对于自主系统(机器人/无人机/汽车)的新兴领域是不可行的,这些系统通常在任务的正确拓扑可能未知或不断变化的环境中运行,并且没有可靠的训练数据。自主系统需要具备模仿人类学习的能力,即我们不断地学习,而且往往是从经验中学习,而不是经过明确的训练。这被称为强化学习(RL)。该项目的目标是在能源受限的自主设备中实现强化学习。如果这项研究成功,将使自动化机器人或无人机大规模扩散,为人类社会提供帮助。学习成果还将用于开发关于机器学习跨层支持的新课程。研究的重点将放在神经进化(NE)上,这是一类使用进化算法进化神经网络拓扑和权重的强化学习算法。这个想法是并行运行多个“父”nn,让环境为所有nn的行为提供奖励(分数),并创建一群新的“子”nn,这些新“子”nn保留来自父节点的节点和连接,这些节点和连接导致行为产生最大的奖励。在多次迭代中运行网元算法已被证明会在神经网络中进化出复杂的行为。不幸的是,网元在计算上非常昂贵,并且在收敛之前需要运行数小时的大规模计算集群。将对神经网络算法的计算和存储行为进行表征,并探索跨基因(即神经网络中的节点和连接)大规模并行化这些算法的机会。交叉和突变的进化学习步骤将在专门的硬件引擎上执行,并将演示在边缘运行NE算法的低功耗架构平台。此外,所提出的研究将为进一步研究快速节能的强化学习算法奠定基础,以帮助实现通用人工智能。
英文摘要
Over the past few years, machine learning algorithms, especially neural networks (NN) have seen a surge of popularity owing to their potential in solving a wide variety of complex problems across image classification and speech recognition. Unfortunately, in order to be effective, NNs need to have the appropriate topology (connections between neurons) for the task at hand and have the right weights on the connections. This is known as supervised learning and requires training the NN by running it through terabytes to petabytes of data. This form of machine learning is infeasible for the emerging domain of autonomous systems (robots/drones/cars) which will often operate in environments where the right topology for the task may be unknown or keep changing, and robust training data is not available. Autonomous systems need the ability to mirror human-like learning, where we are continuously learning, and often from experiences rather than being explicitly trained. This is known as reinforcement learning (RL). The goal of this project will be on enabling RL in energy-constrained autonomous devices. If successful, this research will enable mass proliferation of automated robots or drones to assist human society. The learnings will also be used to develop new courses on cross-layer support for machine learning. The focus of the research will be on neuroevolution (NE), a class of RL algorithms that evolve NN topologies and weights using evolutionary algorithms. The idea is to run multiple "parent" NNs in parallel, have the environment provide a reward (score) to the actions of all NNs, and create a population of new "child" NNs that preserve those nodes and connections from the parents that lead to actions producing the maximum reward. Running NE algorithms over multiple iterations has been shown to evolve complex behaviors in NNs. Unfortunately, NEs are computationally very expensive and have required large scale compute clusters running for hours before converging. A characterization of the computation and memory behavior of NE algorithms will be performed, and opportunities to massively parallelize these algorithms across genes (i.e., nodes and connections in the NN) will be explored. The evolutionary learning steps of crossover and mutation will be performed over specialized hardware engines, and a low-power architectural platform running NE algorithms at the edge will be demonstrated. Furthermore, the proposed research will serve as the foundation for further research in fast and energy-efficient RL algorithms to help realize general-purpose artificial intelligence.
期刊论文(1)
专著(0)
科研奖励(0)
会议论文
DOI:
10.1109/micro.2018.00074
发表时间:
2018-08
期刊:
2018 51st Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)
影响因子:
--
作者:
[A. Samajdar;Parth Mannan;K. Garg;T. Krishna]
通讯作者:
A. Samajdar;Parth Mannan;K. Garg;T. Krishna
Collaborative Research: Frameworks: Advancing Computer Hardware and Systems' Research Capability, Reproducibility, and Sustainability with the gem5 Simulator Ecosystem
-
批准号:2311892
-
项目类别:Standard Grant
-
资助金额:$20.0万
-
财政年份:2023
-
负责人:Tushar Krishna
-
依托单位:
OAC Core: SHF: Small: Enabling Rapid Design and Deployment of Deep Learning Models on Hardware Accelerators
-
批准号:1909900
-
项目类别:Standard Grant
-
资助金额:$50.0万
-
财政年份:2019
-
负责人:Tushar Krishna
-
依托单位:
Student Travel Support for the 2018 Parallel Architectures and Compilation Techniques (PACT-18) Conference
-
批准号:1842928
-
项目类别:Standard Grant
-
资助金额:$1.5万
-
财政年份:2018
-
负责人:Tushar Krishna
-
依托单位:
Student Travel Support for the 2017 International Symposium on Computer Architecture (ISCA-44)
-
批准号:1738358
-
项目类别:Standard Grant
-
资助金额:$1.5万
-
财政年份:2017
-
负责人:Tushar Krishna
-
依托单位:
国内基金
海外基金
天然超短抗菌肽Temporin-SHf衍生多肽的构效分析与抗菌机制研究
-
批准号:
-
项目类别:省市级项目
-
资助金额:--
-
批准年份:2024
-
负责人:唐滋 一
-
依托单位:
衔接蛋白SHF负向调控胶质母细胞瘤中EGFR/EGFRvIII再循环和稳定性的功能及机制研究
-
批准号:82302939
-
项目类别:青年科学基金项目
-
资助金额:30万元
-
批准年份:2023
-
负责人:汪京京
-
依托单位:
EGFR/GRβ/Shf调控环路在胶质瘤中的作用机制研究
-
批准号:81572468
-
项目类别:面上项目
-
资助金额:60.0万元
-
批准年份:2015
-
负责人:邹健
-
依托单位: