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

Name: Deep multi-object symbol learning with self-attention based predictors
Author: Ahmetoğlu, A., Öztop, Erhan, Uğur, E.

İsim	Deep multi-object symbol learning with self-attention based predictors
Yazar	Ahmetoğlu, A., Öztop, Erhan, Uğur, E.
Basım Tarihi:	2023
Basım Yeri	- IEEE
Konu	Deep learning, Robotics, Symbol learning
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	979-835034355-7
Kayıt Numarası	929c084c-4a15-4acf-9f4a-40ba2c11c3b9
Lokasyon	Computer Science
Tarih	2023
Örnek Metin	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

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

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

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

Basım Tarihi 2023

Basım Yeri - IEEE

Konu Deep learning, Robotics, Symbol learning

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 979-835034355-7

Kayıt Numarası 929c084c-4a15-4acf-9f4a-40ba2c11c3b9

Lokasyon Computer Science

Tarih 2023

Örnek Metin 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