基于能量调制学习进度的交错多任务学习
Interleaved Multitask Learning with Energy Modulated Learning Progress
AI总结：
提出以学习进度和神经计算能量消耗驱动任务切换的交错多任务学习架构，并在模拟机械手机器人效果预测任务中验证其准确率与能效优势。
摘要：
人类在学习新技能并运用已有知识的同时，会保持此前习得的信息；机器学习中的“持续学习”也旨在吸收新数据，同时保留并利用过去的知识。然而，现有机器学习方法往往不能模仿人类学习：在人类学习中，任务会因个人偏好和环境条件而相互交织。人类通常会在不同任务之间切换，而不是在完全掌握一个任务后再进入下一个任务。为探索类人的任务切换如何提高学习效率，我们提出一种多任务学习架构，该架构依据“学习进度”和“神经计算能量消耗”等任务无关度量在任务之间交替。为评估方法有效性，我们使用一组由模拟机械手机器人执行的效果预测任务开展了多项系统性实验。实验表明，在平均学习准确率方面，我们的方法优于随机交错任务学习和顺序任务学习。此外，通过将能量消耗纳入任务切换逻辑，我们的方法在降低神经能量消耗的同时仍能保持良好表现。
英文摘要：
As humans learn new skills and apply their existing knowledge while maintaining previously learned information, "continual learning" in machine learning aims to incorporate new data while retaining and utilizing past knowledge. However, existing machine learning methods often does not mimic human learning where tasks are intermixed due to individual preferences and environmental conditions. Humans typically switch between tasks instead of completely mastering one task before proceeding to the next. To explore how human-like task switching can enhance learning efficiency, we propose a multi task learning architecture that alternates tasks based on task-agnostic measures such as "learning progress" and "neural computational energy expenditure". To evaluate the efficacy of our method, we run several systematic experiments by using a set of effect-prediction tasks executed by a simulated manipulator robot. The experiments show that our approach surpasses random interleaved and sequential task learning in terms of average learning accuracy. Moreover, by including energy expenditure in the task switching logic, our approach can still perform favorably while reducing neural energy expenditure.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
