Kolmogorov-Arnold Networks

Terms from Artificial Intelligence: humans at the heart of algorithms

Page numbers are for draft copy at present; they will be replaced with correct numbers when final book is formatted. Chapter numbers are correct and will not change now.

Kolmogorov-Arnold Networks are practical neural networks based on the Kolmogorov-Arnold representation theorem, which have shown promising early results.. They use simplified forms of the more complex non-linear functions required by the theorem to craete networks with only a few layers that can efficiently solve complex problems. The network is an example of the use of non-linear diversity.

Used in Chap. 7: pages 107, 108

Also known as KAN