Prezentare
     Distinctii / Awards
     Departamente
     Cercetare
     Parteneri
     Alumni
     Sustenabilitate
     Oferta educationala
     Studenti
     Admitere
     Examen finalizare studii
     International
     Alegeri academice


Gabriela Bodea,, Clash-ul crizelor sau viclenia lumii asimetrice (Ediția a doua), Presa Universitară Clujeană, 2023
vezi si alte aparitii editoriale

Facebook LinkedIn Twitter
Contact
Str. Teodor Mihali, Nr. 58-60 400591,
Cluj Napoca, Romania
Tel: +40 264-41.86.55
Fax: +40 264-41.25.70

   
Universitatea Babes-Bolyai | Noutati UBB
FSEGA Online | FSEGA SIS | FSEGA Alumni | Sustenabilitate
Executive Education | FSEGA Student Job Market
Contact | Harta Site | Viziteaza FSEGA

Nistor, S.C., Jaradat, M. & Nistor, R.L. (2023) IEEE Access [Info Economics, Q2]

Autor: Cristina Alexandrina Stefanescu

Publicat: 17 Noiembrie 2023


Nistor, S.C., Jaradat, M. & Nistor, R.L. (2023) Developing an Algorithm for Fast Performance Estimation of Recurrent Memory Cells. IEEE Access, 11, 2169-3536.

DOI: https://doi.org/10.1109/ACCESS.2023.3322367

✓ Publisher: IEEE
✓ Categories: Computer Science, Information Systems; Engineering, Electrical & Electronic; Telecommunications
✓ Article Influence Score (AIS): 0.698 (2023) / Q2 in all categories

Abstract: We propose a novel graph-oriented machine learning algorithm which we use for estimating the performance of a recurrent memory cell on a given task. Recurrent neural networks have been successfully used for solving numerous tasks and usually, for each new problem, generic architectures are used. Adapting the architecture could provide superior results, but would be time-consuming if it would not be automated. Neural architecture search algorithms aim at optimizing the architectures for each specific task, but without a fast performance estimation strategy it is difficult to discover high-quality architectures, as evaluating each candidate takes a long period of time. As a case study, we selected the task of sentiment analysis on tweets. Analyzing the sentiments expressed in posts on social networks offers important insights into what are the opinions on different topics and this has applications in numerous domains. We present the architecture of the estimation algorithm, discussing each component. Using this algorithm, we were able to evaluate one million recurrent memory cell architectures and we discovered novel designs that obtain good performances on sentiment analysis. We describe the discovered design that obtains the best performances. We also describe the methodology that we designed, such that it can be applied to other tasks.



inapoi la stiri   vezi evenimentele   home


       Copyright © 08-10-2024 FSEGA. Protectia datelor cu caracter personal FSEGA. Protectia datelor cu caracter personal UBB.
       Web Developer  Dr. Daniel Mican   Graphic Design  Mihai-Vlad Guta