Performance analysis of meta-learning based bayesian deep kernel transfer methods for regression tasks

Name: Performance analysis of meta-learning based bayesian deep kernel transfer methods for regression tasks
Author: Savaşlı, Ahmet Çağatay, Tütüncü, Damla, Ndigande, Alain Patrick, Özer, Sedat

İsim	Performance analysis of meta-learning based bayesian deep kernel transfer methods for regression tasks
Yazar	Savaşlı, Ahmet Çağatay, Tütüncü, Damla, Ndigande, Alain Patrick, Özer, Sedat
Basım Tarihi:	2023
Basım Yeri	- IEEE
Konu	Deep kernel transfer, Few-shot learning, Kernel learning, Meta-learning, Regression
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	2-s2.0-85173554810
Kayıt Numarası	2566dcf4-ecca-490e-ab6d-ba9fa28c9fa9
Lokasyon	Computer Science
Tarih	2023
Örnek Metin	Meta-learning aims to apply existing models on new tasks where the goal is 'learning to learn' so that learning from a limited amount of labeled data or learning in a short amount of time is possible. Deep Kernel Transfer (DKT) is a recently proposed meta-learning approach based on Bayesian framework. DKT's performance depends on the used kernel functions and it has two implementations, namely DKT and GPNet. In this paper, we use a large set of kernel functions on both DKT and GPNet implementations for two regression tasks to study their performances and train them under different optimizers. Furthermore, we compare the training time of both implementations to clarify the ambiguity in terms of which algorithm runs faster for the regression based tasks.
DOI	10.1109/SIU59756.2023.10224015

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Performance analysis of meta-learning based bayesian deep kernel transfer methods for regression tasks

Yazar Savaşlı, Ahmet Çağatay, Tütüncü, Damla, Ndigande, Alain Patrick, Özer, Sedat

Basım Tarihi 2023

Basım Yeri - IEEE

Konu Deep kernel transfer, Few-shot learning, Kernel learning, Meta-learning, Regression

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 2-s2.0-85173554810

Kayıt Numarası 2566dcf4-ecca-490e-ab6d-ba9fa28c9fa9

Lokasyon Computer Science

Tarih 2023

Örnek Metin Meta-learning aims to apply existing models on new tasks where the goal is 'learning to learn' so that learning from a limited amount of labeled data or learning in a short amount of time is possible. Deep Kernel Transfer (DKT) is a recently proposed meta-learning approach based on Bayesian framework. DKT's performance depends on the used kernel functions and it has two implementations, namely DKT and GPNet. In this paper, we use a large set of kernel functions on both DKT and GPNet implementations for two regression tasks to study their performances and train them under different optimizers. Furthermore, we compare the training time of both implementations to clarify the ambiguity in terms of which algorithm runs faster for the regression based tasks.

DOI 10.1109/SIU59756.2023.10224015