paper-with-me

홈 › Papers

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

2022-01-14 · Dimitrios C. Gklezakos, Rajesh P. N. Rao

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.

📄 PDF Abstract BibTeX arXiv:2201.08813

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

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

2022-10-23 · Rajesh P. N. Rao, Dimitrios C. Gklezakos, Vishwas Sathish

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…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Self-Supervised Learning

Bayesian Active Learning for Classification and Preference Learning

2011-12-24 · Neil Houlsby, Ferenc Huszár, Zoubin Ghahramani, Máté Lengyel

Information theoretic active learning has been widely studied for probabilistic models. For simple regression an optimal myopic policy is easily tractable. However, for other tasks and with more complex models, such as c…

Active LearningClassificationGeneral Classification

Causal Tracking of Distributions in Wasserstein Space: A Model Predictive Control Scheme

2024-03-23 · Max Emerick, Jared Jonas, Bassam Bamieh

We consider a problem of optimal swarm tracking which can be formulated as a tracking problem for distributions in the Wasserstein space. Optimal solutions to this problem are non-causal and require knowing the time-traj…

Model Predictive Control

Evaluation of Seed Set Selection Approaches and Active Learning Strategies in Predictive Coding

2019-06-11 · Christian J. Mahoney, Nathaniel Huber-Fliflet, Haozhen Zhao, Jianping Zhang 외

Active learning is a popular methodology in text classification - known in the legal domain as "predictive coding" or "Technology Assisted Review" or "TAR" - due to its potential to minimize the required review effort to…

Active LearningClusteringTARtext-classification+1

Interactively Learning Preference Constraints in Linear Bandits

2022-06-10 · David Lindner, Sebastian Tschiatschek, Katja Hofmann, Andreas Krause

We study sequential decision-making with known rewards and unknown constraints, motivated by situations where the constraints represent expensive-to-evaluate human preferences, such as safe and comfortable driving behavi…

Decision MakingSequential Decision Making