Active Predictive Coding Networks: A Neural Solution to the Problem of Learning Reference Frames and Part-Whole Hierarchies

by   Dimitrios C. Gklezakos, et al.

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.


page 5

page 10

page 12

page 13

page 14


Active Predictive Coding: A Unified Neural Framework for Learning Hierarchical World Models for Perception and Planning

Predictive coding has emerged as a prominent model of how the brain lear...

Recursive Neural Programs: Variational Learning of Image Grammars and Part-Whole Hierarchies

Human vision involves parsing and representing objects and scenes using ...

Exploiting Spatio-Temporal Structure with Recurrent Winner-Take-All Networks

We propose a convolutional recurrent neural network, with Winner-Take-Al...

HEVC Inter Coding Using Deep Recurrent Neural Networks and Artificial Reference Pictures

The efficiency of motion compensated prediction in modern video codecs h...

Unsupervised Learning of Visual Structure using Predictive Generative Networks

The ability to predict future states of the environment is a central pil...

Learning a Driving Simulator's approach to Artificial Intelligence for self-driving cars is ...

Please sign up or login with your details

Forgot password? Click here to reset