由陆军资助的研究增强了对AI系统的记忆

A project of the U.S. Army has developed a new framework for deep neural networks that allows artificial intelligence systems to better learn new tasks while forgetting less of what they have learned in previous tasks.

由陆军资助的北卡罗来纳州立大学的研究人员还表明，使用该框架学习新任务可以使AI更好地执行以前的任务，这一现象称为向后转移。

“The Army needs to be prepared to fight anywhere in the world so its intelligent systems also need to be prepared,” said Dr. Mary Anne Fields, program manager for Intelligent Systems at Army Research Office, an element of U.S. Army Combat Capabilities Development Command’s Army Research Lab. “We expect the Army’s intelligent systems to continually acquire new skills as they conduct missions on battlefields around the world without forgetting skills that have already been trained. For instance, while conducting an urban operation, a wheeled robot may learn new navigation parameters for dense urban cities, but it still needs to operate efficiently in a previously encountered environment like a forest.”

研究团队提出了一个新框架，称为“学习成长”，以持续学习，该框架将网络结构学习和模型参数学习取消。在实验测试中，它的表现优于以前的持续学习方法。

“深层神经网络的人工智能系统是专为learning narrow tasks,” said Xilai Li, a co-lead author of the paper and a Ph.D. candidate at NC State. “As a result, one of several things can happen when learning new tasks, systems can forget old tasks when learning new ones, which is called catastrophic forgetting. Systems can forget some of the things they knew about old tasks, while not learning to do new ones as well. Or systems can fix old tasks in place while adding new tasks — which limits improvement and quickly leads to an AI system that is too large to operate efficiently. Continual learning, also called lifelong-learning or learning-to-learn, is trying to address the issue.”

要了解学习成长框架，请将深层神经网络视为装满多层的管道。原始数据进入管道的顶部，任务输出的底部出现在底部。管道中的每个“层”都是一个计算，可以操纵数据以帮助网络完成其任务，例如在数字图像中识别对象。在管道中排列层有多种方式，这与网络的不同“体系结构”相对应。

当要求深层神经网络学习新任务时，学习成长框架首先是通过搜索进行称为明确的神经体系结构优化的东西。这意味着，随着网络进入系统中的每一层，它可以决定做四件事之一：跳过该层；以与先前任务使用的方式相同的方式使用层；将轻巧的适配器连接到该层，该适配器会稍微修改。或创建一个全新的层。

该架构优化有效地列出了完成新任务所需的最佳拓扑或一系列层。一旦完成，网络就会使用新拓扑来训练如何完成任务，就像其他任何深度学习AI系统一样。

“We’ve run experiments using several data sets, and what we’ve found is that the more similar a new task is to previous tasks, the more overlap there is in terms of the existing layers that are kept to perform the new task,” Li said. “What is more interesting is that, with the optimized — or “learned” topology — a network trained to perform new tasks forgets very little of what it needed to perform the older tasks, even if the older tasks were not similar.”

研究人员还进行了实验，将学习与其他几种持续学习方法相比，将学习框架学习新任务的能力进行比较，并发现在完成新任务时，学习增长框架的准确性更好。

To test how much each network may have forgotten when learning the new task, the researchers then tested each system’s accuracy at performing the older tasks — and the Learn to Grow framework again outperformed the other networks.

Salesforce Research研究总监，工作合着者Caimg Xiong说：“在某些情况下，学习成长的框架实际上在执行旧任务方面变得更好。”“这称为向后转移，并且当您发现学习新任务会使您在旧任务中更好时发生。我们一直在人们看到这一点。AI并不多。”

菲尔兹说：“这项陆军投资扩展了现行的机器学习技术，该技术将指导我们的陆军研究实验室研究人员开发机器人应用，例如智能操作和学习识别新颖对象。”“这项研究使AI更接近为我们的战士提供可以在该领域部署的有效无人系统。”

该论文“学会成长：克服灾难性遗忘的持续结构学习框架”，将在6月9日至15日在加利福尼亚州长滩举行的第36届国际机器学习会议上介绍。该论文的共同领导作者是NC State的电气和计算机工程助理教授Tianfu Wu，Xilai Li，NC State的博士生Xilai Li和Salesforce Research的Yingbo Zhou。该论文是由理查德·索切尔（Richard Socher）合着的，并为Salesforce Research的Caiming caiming。

这项工作也得到了国家科学基金会的支持。一部分工作是在Li是Salesforce AI Research的暑期实习生时完成的。