CRII: SHF: Enabling Neuroevolution in Hardware

CRII：SHF：在硬件中实现神经进化

• 批准号: 1755876
• 负责人: Tushar Krishna
• 金额: $ 17.5万
• 依托单位: Georgia Tech Research Corporation
• 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
• 起止时间: 2018-01-15 至 2019-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1755876&HistoricalAwards=false
• 关键词: CRII; SHF; Enabling; Neuroevolution; Hardware

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.

在过去的几年中，机器学习算法，尤其是神经网络（NN），由于它们在解决图像分类和语音识别方面解决了各种复杂问题的潜力，因此人们看到了广受欢迎的信息。不幸的是，为了有效，NNS需要对手头任务具有适当的拓扑（神经元之间的连接），并在连接上具有正确的权重。这被称为有监督的学习，需要通过通过trabytes将其运行到数据的数据来培训NN。这种机器学习形式对于自主系统（机器人/无人机/汽车）的新兴域而言是不可行的，该域通常会在适用于任务的正确拓扑的环境中运行，或者继续进行更改，并且不可用。自主系统需要能够反映我们持续学习的人类学习的能力，并且通常是从经验而不是接受明确训练的能力。这被称为增强学习（RL）。该项目的目标将是在能源约束的自主设备中启用RL。如果成功，这项研究将使自动机器人或无人机的大规模扩散以协助人类社会。这些学习还将用于开发有关机器学习跨层支持的新课程。该研究的重点将放在神经进化（NE）上，NE，这是一类使用进化算法进化NN拓扑和权重的RL算法。 这个想法是在并行运行多个“父” NN，使环境为所有NNS的行为提供了奖励（分数），并创建一个新的“孩子” NNS人群，从而保留了来自父母的这些节点和连接的新“孩子”，从而导致行动产生最大的奖励。已显示在多个迭代上运行NE算法可以在NNS中发展复杂的行为。不幸的是，NES在计算上非常昂贵，并且需要大规模计算簇在收敛之前运行数小时。将执行NE算法的计算和记忆行为的表征，并将探索跨基因（即NN中的节点和连接）大规模平行这些算法的机会。跨界和突变的进化学习步骤将通过专业的硬件引擎执行，并且将展示在边缘运行NE算法的低功耗架构平台。此外，拟议的研究将为快速和节能的RL算法进行进一步研究的基础，以帮助实现通用人工智能。

项目成果

GeneSys: Enabling Continuous Learning through Neural Network Evolution in Hardware

• DOI: 10.1109/micro.2018.00074
• 发表时间: 2018-08
• 期刊: 2018 51st Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)
• 作者: A. Samajdar;Parth Mannan;K. Garg;T. Krishna