On the Kolmogorov neural networks
arXiv:2311.00049v133 citationsh-index: 15
Originality Synthesis-oriented
AI Analysis
This addresses the theoretical expressiveness of neural networks for researchers in machine learning theory, but it appears incremental as it builds on known Kolmogorov models.
The paper demonstrates that a Kolmogorov two-hidden-layer neural network with specific activation functions can exactly represent various types of multivariate functions, including continuous, discontinuous bounded, and unbounded ones.
In this paper, we show that the Kolmogorov two hidden layer neural network model with a continuous, discontinuous bounded or unbounded activation function in the second hidden layer can precisely represent continuous, discontinuous bounded and all unbounded multivariate functions, respectively.