Abstract
Artificial neural networks are just mathematical functions used for approximation purposes, and learning is a euphemism for determining the parameters of these functions. Experience from other areas of approximation theory shows that closed-form approximation functions determined globally such as neural networks tend to be quite rippled and are, thus, outperformed by approximation functions defined locally. With respect to artificial intelligence, neural networks lack explainability. Therefore, research in novel approaches for local approximators apt to replace neural networks and to outperform them with respect to accuracy, computational expense and explainability is suggested.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cybenko, G.: Approximation by superpositions of a sigmoidal function. Math. Control Signals Syst. 2(4), 303–314 (1989)
Hornik, K.: Approximation capabilities of multilayer feedforward networks. Neural Netw. 4(2), 251–257 (1991)
Hurst, S.L.: Threshold Logic. Mills & Boon Ltd, London (1971)
Kratsios, A.: The universal approximation property – characterization, construction, representation, and existence. Ann. Math. Artif. Intell. 89, 435–469 (2021). https://doi.org/10.1007/s10472-020-09723-1
Ye, A.: You Don’t Understand Neural Networks Until You Understand the Universal Approximation Theorem – The Proof Behind the Neural Network’s Power. https://medium.com/analytics-vidhya/you-dont-understand-neural-networks-until-you-understand-the-universal-approximation-theorem-85b3e7677126
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Halang, W.A., Komkhao, M., Sodsee, S. (2023). Neural Networks in View of Explainable Artificial Intelligence. In: Unger, H., Schaible, M. (eds) Real-time and Autonomous Systems 2022. Real-Time 2022. Lecture Notes in Networks and Systems, vol 674. Springer, Cham. https://doi.org/10.1007/978-3-031-32700-1_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-32700-1_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-32699-8
Online ISBN: 978-3-031-32700-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)