Litcius/Paper detail

Determining the Number of Neurons in Artificial Neural Networks for Approximation, Trained with Algorithms Using the Jacobi Matrix

Kostadin Yotov, Emil Hadzhikolev, Stanka Hadzhikoleva

2020TEM Journal26 citationsDOIOpen Access PDF

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 𝑺τˆΊπ’›τˆ» τ€΅Œ Ξ£ τˆΎπ‹π’Š π’Ž τˆΊπ’› τˆ»τˆΏπŸ π’Šτ€­€πŸ that satisfy the inequality 𝒑 τ€΅‘ π’Ž, 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.

Topics & Concepts

Artificial neural networkCurse of dimensionalityLimit (mathematics)AlgorithmComputer scienceMatrix (chemical analysis)Type (biology)Artificial intelligenceTask (project management)MathematicsEngineeringMathematical analysisMaterials scienceSystems engineeringComposite materialBiologyEcologyNeural Networks and ApplicationsAdvanced Computational Techniques in Science and EngineeringAdvanced Data Processing Techniques