Predictive coding has emerged as a prominent model of how the brain learns through predictions, anticipating the importance accorded to predictive learning in recent AI architectures such as transformers. Here we propose a new framework for predictive coding called active predictive coding which can learn hierarchical world models and solve two radically different open problems in AI: (1) how do we learn compositional representations, e.g., part-whole hierarchies, for equivariant vision? and (2) how do we solve large-scale planning problems, which are hard for traditional reinforcement learning, by composing complex action sequences from primitive policies? Our approach exploits hypernetworks, self-supervised learning and reinforcement learning to learn hierarchical world models that combine task-invariant state transition networks and task-dependent policy networks at multiple abstraction levels. We demonstrate the viability of our approach on a variety of vision datasets (MNIST, FashionMNIST, Omniglot) as well as on a scalable hierarchical planning problem. Our results represent, to our knowledge, the first demonstration of a unified solution to the part-whole learning problem posed by Hinton, the nested reference frames problem posed by Hawkins, and the integrated state-action hierarchy learning problem in reinforcement learning.
翻译:预测性编码是大脑如何通过预测来学习的突出模型,预示着预测性学习在诸如变异器等最近的AI结构中的重要性。在这里,我们提出了一个新的预测性编码框架,称为主动预测性编码,可以学习等级世界模式,解决AI中两个完全不同的开放问题:(1) 我们如何学习构成性表述,例如半整体等级,以获得等式愿景?(2) 我们如何解决大规模规划问题,这些问题对于传统的强化学习来说是困难的?我们的方法是利用超网络、自我监督的学习和强化学习学习,学习等级世界模式,这些模式将任务变化状态过渡网络和任务独立的政策网络结合到多个抽象层面。我们展示了我们对各种视觉数据集(例如,半整体结构图、法西昂-MNIST、Omniglot)以及可伸缩的等级规划问题(对于传统的强化学习来说是困难的)所采取的办法的可行性。根据我们的知识,我们的方法是利用超网络、自我监督的学习和强化学习的学习方法,这是通过Hin的学习模型构成的软体学习问题。