Vol.9, No.4, November 2020. ISSN: 2217-8309 eISSN: 2217-8333
TEM Journal
TECHNOLOGY, EDUCATION, MANAGEMENT, INFORMATICS Association for Information Communication Technology Education and Science |
Determining the Number of Neurons in Artificial Neural Networks for Approximation, Trained with Algorithms Using the Jacobi Matrix
Kostadin Yotov, Emil Hadzhikolev, Stanka Hadzhikoleva
Β© 2020 Stanka Hadzhikoleva, published by UIKTEN. This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. (CC BY-NC-ND 4.0)
Citation Information: TEM Journal. Volume 9, Issue 4, Pages 1320-1329, ISSN 2217-8309, DOI: 10.18421/TEM94-02, November 2020.
Received: 09 September 2020. Revised: 19 October 2020.
Abstract:
How can we determine the optimal number of neurons when constructing an artificial neural network? This is one of the most frequently asked questions when working with this type of artificial intelligence. Experience has brought the understanding that it takes an individual approach for each task to specify the number of neurons. Our method is based on the requirement of algorithms looking for a minimum of functions of type πΊτΊπτ» τ΅ Ξ£ τΎππ π τΊπ τ»τΏπ πτπ that satisfy the inequality π τ΅ π, where p is the dimensionality of the argument z, and m is the number of functions. Formulas for an upper limit of the required neurons are proposed for networks with one hidden layer and for networks with r hidden layers with an equal number of neurons.
Keywords –neural networks for approximation, number of neurons, neural network design. |
----------------------------------------------------------------------------------------------------------- ----------------------------------------------------------------------------------------------------------- |