New voting functions for neural network algorithms

Tajti, Tibor (2020) New voting functions for neural network algorithms Annales Mathematicae et Informaticae. pp. 229-242. ISSN 1787-6117 (Online)

pdf AMI_52_from229to242.pdf Download (690kB) [error in script]

Absztrakt (kivonat)

Neural Network and Convolutional Neural Network algorithms are among the best performing machine learning algorithms. However, the performance of the algorithms may vary between multiple runs because of the stochastic nature of these algorithms. This stochastic behavior can result in weaker accuracy for a single run, and in many cases, it is hard to tell whether we should repeat the learning giving a chance to have a better result. Among the useful techniques to solve this problem, we can use the committee machine and the ensemble methods, which in many cases give better than average or even better than the best individual result. We defined new voting function variants for ensemble learner committee machine algorithms which can be used as competitors of the well-known voting functions. Some belong to the locally weighted average voting functions, others are meta voting functions calculated from the output of the previous voting functions functions called with the results of the individual learners. The performance evaluation of these methods was done from numerous learning sessions.

Mű típusa:	Folyóiratcikk - Journal article
Szerző:	Szerző neve Email MTMT azonosító ORCID azonosító Közreműködés Tajti, Tibor NEM RÉSZLETEZETT NEM RÉSZLETEZETT NEM RÉSZLETEZETT Szerző
Kapcsolódó URL-ek:	Folyóirat honlapja
Kulcsszavak:	Machine learning, neural networks, committee machines, ensemble methods
Nyelv:	angol
DOI azonosító:	10.33039/ami.2020.10.003
ISSN:	1787-6117 (Online)
Felhasználó:	Tibor Gál
Dátum:	22 Okt 2020 06:39
Utolsó módosítás:	17 Dec 2020 14:06
URI:	http://publikacio.uni-eszterhazy.hu/id/eprint/6657

Műveletek (bejelentkezés szükséges)

Tétel nézet