通过提供激励和练习来克服人工神经网络的经典挑战
Overcoming classic challenges for artificial neural networks by providing incentives and practice
AI总结：
本文综述了如何利用元学习为机器提供“激励与练习”以克服人工神经网络在系统泛化、灾难性遗忘、少样本学习和多步推理等方面的经典挑战，并探讨了大语言模型对该框架的体现及对理解人类发展的启示。
摘要：
自从最早提出关于心智和大脑的人工神经网络（ANN）模型以来，批评者就指出了这些模型与人类认知能力相比存在的关键弱点。在此，我们回顾了近期使用元学习来克服几个经典挑战的研究，我们将其特征化为解决“激励与练习问题”——即，为机器提供改进特定技能的激励以及练习这些技能的机会。这种显式优化与更传统的方法形成对比，后者希望通过优化相关但不同的目标来使期望的行为得以涌现。我们回顾了这一原理在解决ANN的四个经典挑战上的应用：系统泛化、灾难性遗忘、少样本学习和多步推理。我们还讨论了大型语言模型如何结合这一元学习框架的关键方面（即，在多样化数据上训练并带有反馈的序列预测），这有助于解释它们在应对这些经典挑战上取得的一些成功。最后，我们讨论了通过这一框架理解人类发展各个方面的前景，以及自然环境是否为学习如何做出具有挑战性的泛化提供了正确的激励和练习。
英文摘要：
Since the earliest proposals for artificial neural network (ANN) models of the mind and brain, critics have pointed out key weaknesses in these models compared to human cognitive abilities. Here we review recent work that uses metalearning to overcome several classic challenges, which we characterize as addressing the Problem of Incentive and Practice -- that is, providing machines with both incentives to improve specific skills and opportunities to practice those skills. This explicit optimization contrasts with more conventional approaches that hope the desired behaviour will emerge through optimizing related but different objectives. We review applications of this principle to addressing four classic challenges for ANNs: systematic generalization, catastrophic forgetting, few-shot learning and multi-step reasoning. We also discuss how large language models incorporate key aspects of this metalearning framework (namely, sequence prediction with feedback trained on diverse data), which helps to explain some of their successes on these classic challenges. Finally, we discuss the prospects for understanding aspects of human development through this framework, and whether natural environments provide the right incentives and practice for learning how to make challenging generalizations.
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。
