BARUAH, MURCHANA and BANERJEE, BONNY and Nagar, Atulya K. (2022) An Attention-Based Predictive Agent for Static and Dynamic Environments. IEEE Access. ISSN 2169-3536
Preview |
Text (Open Access publication in IEEE Access)
IEEEAccess_Baruah;Banerjee;Nagar.pdf - Published Version Available under License Creative Commons Attribution. Download (1MB) | Preview |
Abstract
Real-world applications of intelligent agents demand accuracy and efficiency, and seldom provide reinforcement signals. Currently, most agent models are reinforcement-based and concentrate exclusively on accuracy. We propose a general-purpose agent model consisting of proprioceptive and perceptual pathways. The agent actively samples its environment via a sequence of glimpses. It completes the partial propriocept and percept sequences observed till each sampling instant, and learns where and what to sample by minimizing prediction error, without reinforcement or supervision (class labels). The model is evaluated by exposing it to two kinds of stimuli: images of fully-formed handwritten numerals and alphabets, and videos of gradual formation of numerals. It yields state-of-the-art prediction accuracy upon sampling only 22:6% of the scene on average. The model saccades when exposed to images and tracks when exposed to videos. This is the first known attention-based agent to generate realistic handwriting with state-of-the-art
accuracy and efficiency by interacting with and learning end-to-end from static and dynamic environments.
| Item Type: | Article |
|---|---|
| Additional Information and Comments: | This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2022.3149585, IEEE Access. |
| Keywords: | Agent, attention, handwriting generation, multimodal, perception, proprioception |
| Faculty / Department: | Faculty of Human and Digital Sciences > Mathematics and Computer Science |
| Depositing User: | Atulya Nagar |
| Date Deposited: | 16 Feb 2022 15:51 |
| Last Modified: | 16 Feb 2022 15:51 |
| URI: | https://hira.hope.ac.uk/id/eprint/3488 |
Actions (login required)
 |
View Item |
Altmetric
Altmetric
