Model of optimizing the multistage process of neuronet training with wastage constraint function in an image recognition problem
Abstract
On a pattern of neuronet investigation of the colored image recognition problem the problem of bringing the fastest information processing system to the optimal mode of functioning by conditions of preliminarily unknown distribution of priorities of its parameters is considered in the paper. There has been formalized the corresponding decision making problem, in which alternatives are methods of training the neural network, and its parameters are interpreted as aftereffects. Reasoning from absence of probability measures over the set of indeterminate parameters of the information processing system, throughout the given decision making problem there is solved a matrix game, in which the second player of optimal strategy is used for combined selection of methods of training the neural network, not depending on amount of its being estimated parameters. There has been displayed the advantage of a model of optimizing the multistage process of neuronet training with wastage constraint function in comparison to the clas-sic model of optimal strategy realization, and also to the training method, at which the minimal distance to the utopia point is reached.References
1. Трухаев Р. И. Модели принятия решений в условиях неопределённости / Р. И. Трухаев. — М. : Наука, 1981. — 258 с.
2. Теория игр : учеб. пос. для ун-тов / [Л. А. Петросян, Н. А. Зенкевич, Е. А. Семина]. — М. : Высшая школа, Книж-
ный дом «Университет», 1998. — 304 с.
3. Хайкин С. Нейронные сети: полный курс / С. Хайкин. — 2-е изд. — М. : Издательский дом «Вильямс», 2006. — 1104 с.
4. Xudong Jiang. Constructing and training feed-forward neural networks for pattern classification / Xudong Jiang, Alvin
Harvey Kam Siew Wah // Pattern Recognition. — 2003. — Vol. 36, Issue 4. — P. 853—867.
5. Goltsev A. Investigation of efficient features for image recognition by neural networks / A. Goltsev, V. Gritsenko // Neural
Networks. — 2012. — Vol. 28. — P. 15—23.
6. McLoone S. Improving neural network training solutions using regularisation / S. McLoone, G. Irwin // Neurocomputing.
— 2001. — Vol. 37, Issues 1—4. — P. 71—90.
7. Upper bound of the expected training error of neural network regression for a Gaussian noise sequence /
[K. Hagiwara, T. Hayasaka, N. Toda and other] // Neural Networks. — 2001. — Vol. 14, Issue 10. — Pр. 1419—1429.
8. Romanuke V. V. Finding the probability distribution to minimax single-valued mapping for modeling the being controlled
system parameter / V. V. Romanuke // XI International Conference «MCCS-2012», October 9—11, 2012, Vinnytsya : abstracts.
— Vinnytsya : VNTU, 2012. — P. 7—8.
9. Романюк В. В. Метод реалізації оптимальних змішаних стратегій у матричній грі з порожньою множиною сідлових точок у
чистих стратегіях з відомою кількістю партій гри / В. В. Романюк // Наукові вісті НТУУ «КПІ». — 2009. — № 2. — С. 45—52.
10. Томашевський В. М. Моделювання систем / В. М. Томашевський. — К. : вид. група BHV, 2005. — 352 с.
2. Теория игр : учеб. пос. для ун-тов / [Л. А. Петросян, Н. А. Зенкевич, Е. А. Семина]. — М. : Высшая школа, Книж-
ный дом «Университет», 1998. — 304 с.
3. Хайкин С. Нейронные сети: полный курс / С. Хайкин. — 2-е изд. — М. : Издательский дом «Вильямс», 2006. — 1104 с.
4. Xudong Jiang. Constructing and training feed-forward neural networks for pattern classification / Xudong Jiang, Alvin
Harvey Kam Siew Wah // Pattern Recognition. — 2003. — Vol. 36, Issue 4. — P. 853—867.
5. Goltsev A. Investigation of efficient features for image recognition by neural networks / A. Goltsev, V. Gritsenko // Neural
Networks. — 2012. — Vol. 28. — P. 15—23.
6. McLoone S. Improving neural network training solutions using regularisation / S. McLoone, G. Irwin // Neurocomputing.
— 2001. — Vol. 37, Issues 1—4. — P. 71—90.
7. Upper bound of the expected training error of neural network regression for a Gaussian noise sequence /
[K. Hagiwara, T. Hayasaka, N. Toda and other] // Neural Networks. — 2001. — Vol. 14, Issue 10. — Pр. 1419—1429.
8. Romanuke V. V. Finding the probability distribution to minimax single-valued mapping for modeling the being controlled
system parameter / V. V. Romanuke // XI International Conference «MCCS-2012», October 9—11, 2012, Vinnytsya : abstracts.
— Vinnytsya : VNTU, 2012. — P. 7—8.
9. Романюк В. В. Метод реалізації оптимальних змішаних стратегій у матричній грі з порожньою множиною сідлових точок у
чистих стратегіях з відомою кількістю партій гри / В. В. Романюк // Наукові вісті НТУУ «КПІ». — 2009. — № 2. — С. 45—52.
10. Томашевський В. М. Моделювання систем / В. М. Томашевський. — К. : вид. група BHV, 2005. — 352 с.
Downloads
-
PDF (Українська)
Downloads: 67
Abstract views: 101
How to Cite
[1]
V. V. Romaniuk, “Model of optimizing the multistage process of neuronet training with wastage constraint function in an image recognition problem”, Вісник ВПІ, no. 1, pp. 104–109, Mar. 2013.
Issue
Section
Information technologies and computer sciences
License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
