GeneSys: Enabling Continuous Learning through Neural Network Evolution in Hardware
GeneSys: Enabling Continuous Learning through Neural Network Evolution in Hardware
复制标题
DOI：
10.1109/micro.2018.00074
复制
发表时间：
2018-08
期刊：
影响因子：
--
通讯作者：
A. Samajdar;Parth Mannan;K. Garg;T. Krishna
中科院分区：
文献类型：
--
作者：
A. Samajdar;Parth Mannan;K. Garg;T. Krishna
现代深度学习系统依赖于（a）手动调整的神经网络拓扑，（B）大量标记的训练数据，以及（c）在大规模计算资源上的广泛训练，以构建可以执行有效图像分类或语音识别的系统。不幸的是，我们仍然远离实现自适应通用智能系统，需要在未知的环境中自主学习，可能无法访问这三个组件中的一些或任何一个。基于强化学习和进化算法（EA）的方法通过不断与环境交互并根据获得的奖励更新模型来规避这个问题。然而，在边缘无处不在的自主代理（机器人/无人机）上部署这些算法需要极高的能效，因为（i）紧张的功率和能源预算，（ii）与环境的持续/终身交互，（iii）间歇性或无连接到云来运行重量级处理。为了满足这一需求，我们提出了GENESYS，一个基于EA的学习系统的HW-SW原型，它包括一个闭环学习引擎EvE和一个推理引擎ADAM。EvE可以在硬件中完全进化神经网络的拓扑结构和权重，而不需要手动优化或反向传播训练。ADAM持续与环境交互，并针对EvE生成的不规则神经网络进行了优化。GENESYS识别并利用了EA特有的多个独特的并行途径，我们称之为“基因”级并行和“种群”级并行。我们使用OpenAI gym的一套环境运行GENESYS，并观察到比最先进的嵌入式和桌面CPU和GPU系统高出2-5个数量级的能效。
Modern deep learning systems rely on (a) a hand-tuned neural network topology, (b) massive amounts of labeled training data, and (c) extensive training over large-scale compute resources to build a system that can perform efficient image classification or speech recognition. Unfortunately, we are still far away from implementing adaptive general purpose intelligent systems which would need to learn autonomously in unknown environments and may not have access to some or any of these three components. Reinforcement learning and evolutionary algorithm (EA) based methods circumvent this problem by continuously interacting with the environment and updating the models based on obtained rewards. However, deploying these algorithms on ubiquitous autonomous agents at the edge (robots/drones) demands extremely high energy-efficiency due to (i) tight power and energy budgets, (ii) continuous/lifelong interaction with the environment, (iii) intermittent or no connectivity to the cloud to run heavy-weight processing. To address this need, we present GENESYS, an HW-SW prototype of an EA-based learning system, that comprises a closed loop learning engine called EvE and an inference engine called ADAM. EvE can evolve the topology and weights of neural networks completely in hardware for the task at hand, without requiring hand-optimization or backpropagation training. ADAM continuously interacts with the environment and is optimized for efficiently running the irregular neural networks generated by EvE. GENESYS identifies and leverages multiple unique avenues of parallelism unique to EAs that we term "gene"- level parallelism, and "population"-level parallelism. We ran GENESYS with a suite of environments from OpenAI gym and observed 2-5 orders of magnitude higher energy-efficiency over state-of-the-art embedded and desktop CPU and GPU systems.