Advanced search ?

Object

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

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

Creator:

Ponti, Francesca ; Frezza, Fabrizio ; Simeoni, Patrizio ; Parisi, Raffaele

Date:

2024, nr 3

Resource Type:

artykuł

Group publication title:

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

Number:

3

Publisher:

National Institute of Telecommunications

Resource Identifier:

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

Source:

Journal of Telecommunications and Information Technology

Language:

ang

License:

CC BY 4.0

rights owner:

Instytut Łączności - Państwowy Instytut Badawczy

Subject and keywords:

deep neural networks machine learning optimization

Object collections:

Last modified:

Feb 25, 2026

In our library since:

Oct 2, 2024

Number of object content hits:

199

All available object's versions:

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

Show description in RDF format:

RDF

Show description in OAI-PMH format:

OAI-PMH

Edition name Date
Ponti, Francesca; Frezza, Fabrizio; Simeoni, Patrizio, A Generalized Learning Approach to Deep Neural Networks, Journal of Telecommunications and Information Technology, 2024, nr 3 Feb 25, 2026

Objects Similar
Convolutional Neural Networks for C. Elegans Muscle Age Classification Using Only Self-learned Features, Journal of Telecommunications and Information Technology, 2022, nr 4

Dzwonkowski, Mariusz Czaplewski, Bartosz Panas, Damian

2022, nr 4
artykuł
Analytical Investigation on a New Approach for Achieving Deep Penetration in a Lossy Medium: The Lossy Prism, Journal of Telecommunications and Information Technology, 2017, nr 3

Simeoni, Patrizio Tedeschi, Nicola Frezza, Fabrizio

2017, nr 3
artykuł
Numerical Evaluation of Electromagnetic-wave Penetration at Normal Incidence through an Inhomogeneous-wave Approach, Journal of Telecommunications and Information Technology, 2018, nr 2

Simeoni, Patrizio Tedeschi, Nicola Frezza, Fabrizio Calcaterra, Alessandro

2018, nr 2
artykuł
2026, nr 2, JTIT-artykuły
2026, nr 2, JTIT-artykuły
Evaluating AES Payload Encryption for Securing MQTT-based Smart Home Networks with Machine Learning-based Intrusion Detection, Journal of Telecommunications and Information Technology, 2026, nr 2

Gajewski, Mariusz Sałabun, Wojciech

2026, nr 2
artykuł
2025, nr 3, JTIT-artykuły
2025, nr 3, JTIT-artykuły
A Comprehensive Study on Path Loss Estimation Using Deep Hybrid Learning in 5G Networks, Journal of Telecommunications and Information Technology, 2025, nr 3

Yeaser, Kazi Md Abrar Hassan, Kazi Md Abir

2025, nr 3
artykuł
2026, nr 3, JTIT-artykuły
2026, nr 3, JTIT-artykuły
Explainable Network Traffic Classification Using XGBoost and SHAP: Interpreting Feature Contributions Across Traffic Classes, Journal of Telecommunications and Information Technology, 2026, nr 3

Deghem, Boubakar Seddik Aid, Lahcene Mostefaoui, Kadda

2026, nr 3
artykuł
Contextual probability, Journal of Telecommunications and Information Technology, 2003, nr 3

Wang, Hui

2003, nr 3
artykuł
Manipulation of compressed data using MPEG-7 low level audio descriptors, Journal of Telecommunications and Information Technology, 2003, nr 2

Harders, Nick Perrow, Shane Stirling, David Lukasiak, Jason

2003, nr 2
artykuł
More
×

Citation

Citation style:

Contact details

Address

Instytut Łączności – Państwowy Instytut Badawczy ul. Szachowa 1 04-894 Warszawa

Phone

(+48) 5128 696

E-Mail

biblioteka@il-pib.pl

Visit us!

This page uses 'cookies'. More information