Active Sensing with Predictive Coding and Uncertainty Minimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sharafeldin, Abdelrahman, Imam, Nabil, Choi, Hannah
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909104272834560
author Sharafeldin, Abdelrahman
Imam, Nabil
Choi, Hannah
author_facet Sharafeldin, Abdelrahman
Imam, Nabil
Choi, Hannah
contents We present an end-to-end procedure for embodied exploration inspired by two biological computations: predictive coding and uncertainty minimization. The procedure can be applied to exploration settings in a task-independent and intrinsically driven manner. We first demonstrate our approach in a maze navigation task and show that it can discover the underlying transition distributions and spatial features of the environment. Second, we apply our model to a more complex active vision task, where an agent actively samples its visual environment to gather information. We show that our model builds unsupervised representations through exploration that allow it to efficiently categorize visual scenes. We further show that using these representations for downstream classification leads to superior data efficiency and learning speed compared to other baselines while maintaining lower parameter complexity. Finally, the modularity of our model allows us to probe its internal mechanisms and analyze the interaction between perception and action during exploration.
format Preprint
id arxiv_https___arxiv_org_abs_2307_00668
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Active Sensing with Predictive Coding and Uncertainty Minimization
Sharafeldin, Abdelrahman
Imam, Nabil
Choi, Hannah
Machine Learning
Neural and Evolutionary Computing
We present an end-to-end procedure for embodied exploration inspired by two biological computations: predictive coding and uncertainty minimization. The procedure can be applied to exploration settings in a task-independent and intrinsically driven manner. We first demonstrate our approach in a maze navigation task and show that it can discover the underlying transition distributions and spatial features of the environment. Second, we apply our model to a more complex active vision task, where an agent actively samples its visual environment to gather information. We show that our model builds unsupervised representations through exploration that allow it to efficiently categorize visual scenes. We further show that using these representations for downstream classification leads to superior data efficiency and learning speed compared to other baselines while maintaining lower parameter complexity. Finally, the modularity of our model allows us to probe its internal mechanisms and analyze the interaction between perception and action during exploration.
title Active Sensing with Predictive Coding and Uncertainty Minimization
topic Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2307.00668