Disentangling Shape and Pose for Object-Centric Deep Active Inference Models

09/16/2022
by   Stefano Ferraro, et al.
3

Active inference is a first principles approach for understanding the brain in particular, and sentient agents in general, with the single imperative of minimizing free energy. As such, it provides a computational account for modelling artificial intelligent agents, by defining the agent's generative model and inferring the model parameters, actions and hidden state beliefs. However, the exact specification of the generative model and the hidden state space structure is left to the experimenter, whose design choices influence the resulting behaviour of the agent. Recently, deep learning methods have been proposed to learn a hidden state space structure purely from data, alleviating the experimenter from this tedious design task, but resulting in an entangled, non-interpreteable state space. In this paper, we hypothesize that such a learnt, entangled state space does not necessarily yield the best model in terms of free energy, and that enforcing different factors in the state space can yield a lower model complexity. In particular, we consider the problem of 3D object representation, and focus on different instances of the ShapeNet dataset. We propose a model that factorizes object shape, pose and category, while still learning a representation for each factor using a deep neural network. We show that models, with best disentanglement properties, perform best when adopted by an active agent in reaching preferred observations.

READ FULL TEXT

page 7

page 8

page 13

research
04/14/2023

Symmetry and Complexity in Object-Centric Deep Active Inference Models

Humans perceive and interact with hundreds of objects every day. In doin...
research
08/18/2022

Learning Generative Models for Active Inference using Tensor Networks

Active inference provides a general framework for behavior and learning ...
research
09/24/2019

Demystifying active inference

Active inference is a first (Bayesian) principles account of how autonom...
research
01/30/2020

Learning Perception and Planning with Deep Active Inference

Active inference is a process theory of the brain that states that all l...
research
09/09/2010

Probabilistic Models over Ordered Partitions with Application in Learning to Rank

This paper addresses the general problem of modelling and learning rank ...
research
08/26/2021

Disentangling What and Where for 3D Object-Centric Representations Through Active Inference

Although modern object detection and classification models achieve high ...
research
06/13/2023

Realising Synthetic Active Inference Agents, Part I: Epistemic Objectives and Graphical Specification Language

The Free Energy Principle (FEP) is a theoretical framework for describin...

Please sign up or login with your details

Forgot password? Click here to reset