Kolmogorov-Arnold Networks
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
proposes Kolmogorov-Arnold Networks (KANs) as alternatives to Multi-Layer Perceptrons (MLPs); KANs apply learnable activation functions on edges that represent the weights; with no linear weights used, KANs can outperform MLPs and possess faster neural scaling laws; the authors show that KANs can be used as collaborators to help scientists discover mathematics and physical laws.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack