论文标题
主动预测编码网络：学习参考帧和部分整体层次结构的神经解决方案
Active Predictive Coding Networks: A Neural Solution to the Problem of Learning Reference Frames and Part-Whole Hierarchies
论文作者
论文摘要
我们引入了主动预测编码网络（APCNS），这是一种新的神经网络，解决了Hinton和其他人在人工智能和大脑建模领域提出的主要问题：神经网络如何通过在Parse terse a Parse树中动态分配零件分配的零件分配的零件层次来学习对象的内在参考框架，并将其分解为零件的视觉场景？ APCN通过使用新颖的思想组合来解决这个问题：（1）超级核武器用于动态生成经常性的神经网络，这些神经网络可预测零件及其在固有参考框架内的零件及其位置，该固有参考框架以较高对象级别的嵌入向量为条件，（2）增强学习与重新分类相结合，以用于最终的模型参数。 APCN体系结构自然地适合多层分层学习，并且与皮质功能的预测编码模型密切相关。使用MNIST，时尚摄像机和Omniglot数据集，我们证明APCN可以（a）学会将图像解析为部分整体层次结构，（b）学习构图表示，以及（c）将其知识转移到看不见的对象类别。 APCN具有动态生成带有零件位置的分析树的能力，为可解释的AI提供了一个新的框架，该框架利用了深度学习的进步，同时保留了可解释性和组成性。
We introduce Active Predictive Coding Networks (APCNs), a new class of neural networks that solve a major problem posed by Hinton and others in the fields of artificial intelligence and brain modeling: how can neural networks learn intrinsic reference frames for objects and parse visual scenes into part-whole hierarchies by dynamically allocating nodes in a parse tree? APCNs address this problem by using a novel combination of ideas: (1) hypernetworks are used for dynamically generating recurrent neural networks that predict parts and their locations within intrinsic reference frames conditioned on higher object-level embedding vectors, and (2) reinforcement learning is used in conjunction with backpropagation for end-to-end learning of model parameters. The APCN architecture lends itself naturally to multi-level hierarchical learning and is closely related to predictive coding models of cortical function. Using the MNIST, Fashion-MNIST and Omniglot datasets, we demonstrate that APCNs can (a) learn to parse images into part-whole hierarchies, (b) learn compositional representations, and (c) transfer their knowledge to unseen classes of objects. With their ability to dynamically generate parse trees with part locations for objects, APCNs offer a new framework for explainable AI that leverages advances in deep learning while retaining interpretability and compositionality.
