Symmetry and Complexity in Object-Centric Deep Active Inference Models
Authors:
- Stefano FerraroSFStefano Ferraro
- Bart DhoedtBDBart Dhoedt
Preprint
Abstract
Humans perceive and interact with hundreds of objects every day. In doing so, they need to employ mental models of these objects and often exploit symmetries in the object's shape and appearance in order to learn generalizable and transferable skills. Active inference is a first principles approach to understanding and modeling sentient agents. It states that agents entertain a generative model of their environment, and learn and act by minimizing an upper bound on their surprisal, i.e. their Free Energy. The Free Energy decomposes into an accuracy and complexity term, meaning that agents favor the least complex model, that can accurately explain their sensory observations. In this paper, we investigate how inherent symmetries of particular objects also emerge as symmetries in the latent state space of the generative model learnt under deep active inference. In particular, we focus on object-centric representations, which are trained from pixels to predict novel object views as the agent moves its viewpoint. First, we investigate the relation between model complexity and symmetry exploitation in the state space. Second, we do a principal component analysis to demonstrate how the model encodes the principal axis of symmetry of the object in the latent space. Finally, we also demonstrate how more symmetrical representations can be exploited for better generalization in the context of manipulation.Keywords
All Related Versions
- Version 1, 2023-04-14, ArXiv
- Published version: Interface Focus, 13 (3), 20220077.
This publication has 17 references indexed in Scilit:
- Disentangling Shape and Pose for Object-Centric Deep Active Inference Models2023
- The Developing Infant Creates a Curriculum for Statistical LearningTrends in Cognitive Sciences, 2018
- The Code for Facial Identity in the Primate BrainCell, 2017
- Dimensionality reduction using Principal Component Analysis for network intrusion detectionPerspectives in Science, 2016
- Active inference and learningNeuroscience & Biobehavioral Reviews, 2016
- Simulation as an engine of physical scene understandingProceedings of the National Academy of Sciences, 2013
- The history of the future of the Bayesian brainNeuroImage, 2012
- Generalization in vision and motor controlNature, 2004
- Conjunction and linear non-separability effects in visual shape encodingVision Research, 2000
- Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in positionBiological Cybernetics, 1980