Back to Search

Deep multi-object symbol learning with self-attention based predictors

Title	Deep multi-object symbol learning with self-attention based predictors
Author	Ahmetoğlu, A., Öztop, Erhan, Uğur, E.
Publication Date:	2023
Publication Place	- IEEE
Subject	Deep learning, Robotics, Symbol learning
Type	Document
Language	English
Digital	Yes
Manuscript	No
Library:	Özyeğin University
Library Asset ID	979-835034355-7
Record ID	929c084c-4a15-4acf-9f4a-40ba2c11c3b9
Library Location	Computer Science
Date	2023
Sample Text	This paper proposes an architecture that can learn symbolic representations from the continuous sensorimotor experience of a robot interacting with a varying number of objects. Unlike previous works, this work aims to remove constraints on the learned symbols such as a fixed number of interacted objects or pre-defined symbolic structures. The proposed architecture can learn symbols for single objects and relations between them in a unified manner. The architecture is an encoder-decoder network with a binary activation layer followed by self-attention layers. Experiments are conducted in a robotic manipulation setup with a varying number of objects. Results showed that the robot successfully encodes the interaction dynamics between a varying number of objects using the discovered symbols. We also showed that the discovered symbols can be used for planning to reach symbolic goal states by training a higher-level neural network.
DOI	10.1109/SIU59756.2023.10223865

View in source Özyeğin University Özyeğin University - Historical works, archives, and periodicals search engine

Özyeğin University

Deep multi-object symbol learning with self-attention based predictors

Author Ahmetoğlu, A., Öztop, Erhan, Uğur, E.

Publication Date 2023

Publication Place - IEEE

Subject Deep learning, Robotics, Symbol learning

Type Document

Language English

Digital Yes

Manuscript No

Library Özyeğin University

Library Asset ID 979-835034355-7

Record ID 929c084c-4a15-4acf-9f4a-40ba2c11c3b9

Library Location Computer Science

Date 2023

Sample Text This paper proposes an architecture that can learn symbolic representations from the continuous sensorimotor experience of a robot interacting with a varying number of objects. Unlike previous works, this work aims to remove constraints on the learned symbols such as a fixed number of interacted objects or pre-defined symbolic structures. The proposed architecture can learn symbols for single objects and relations between them in a unified manner. The architecture is an encoder-decoder network with a binary activation layer followed by self-attention layers. Experiments are conducted in a robotic manipulation setup with a varying number of objects. Results showed that the robot successfully encodes the interaction dynamics between a varying number of objects using the discovered symbols. We also showed that the discovered symbols can be used for planning to reach symbolic goal states by training a higher-level neural network.

DOI 10.1109/SIU59756.2023.10223865