Obiekt

Tytuł: A Generalized Learning Approach to Deep Neural Networks, Journal of Telecommunications and Information Technology, 2024, nr 3

Tytuł publikacji grupowej:

2024, nr 3, JTIT-artykuły

Abstrakt:

Optimization of machine learning architectures is essential in determining the efficacy and the applicability of any neural architecture to real world problems. In this work a generalized Newton's method (GNM) is presented as a powerful approach to learning in deep neural networks (DNN). This technique was compared to two popular approaches, namely the stochastic gradient descent (SGD) and the Adam algorithm, in two popular classification tasks. The performance of the proposed approach confirmed it as an attractive alternative to state-of-the-art first order solutions. Due to the good results presented in the case of shallow DNN, in the last part of the article an hybrid optimization Method is presented. This method consists in combining two optimization algorithms, i.e. GNM and Adam or GNM and SGD, during the training phase within the layers of the neural network. This configuration aims to benefit from the strengths of both first- and second-order algorithms. In this case a convolutional neural network is considered and its parameters are updated with a different optimization algorithm. Also in this case, the hybrid approach returns the best performance with respect to the first order algorithms

Numer:

3

Wydawca:

National Institute of Telecommunications

Identyfikator zasobu:

oai:bc.itl.waw.pl:2353 ; ISSN 1509-4553, on-line: ISSN 1899-8852

DOI:

10.26636/jtit.2024.3.1454

ISSN:

1509-4553

eISSN:

1899-8852

Źródło:

Journal of Telecommunications and Information Technology

Język:

ang

Licencja:

CC BY 4.0

Właściciel praw:

Instytut Łączności - Państwowy Instytut Badawczy

Kolekcje, do których przypisany jest obiekt:

Data ostatniej modyfikacji:

2 paź 2024

Data dodania obiektu:

2 paź 2024

Liczba wyświetleń treści obiektu:

18

Wszystkie dostępne wersje tego obiektu:

https://bc.itl.waw.pl/publication/2666

Wyświetl opis w formacie RDF:

RDF

Wyświetl opis w formacie OAI-PMH:

OAI-PMH

Obiekty Podobne

×

Cytowanie

Styl cytowania:

Ta strona wykorzystuje pliki 'cookies'. Więcej informacji