paper-with-me

홈 › Papers

The Proof of Kolmogorov-Arnold May Illuminate Neural Network Learning

2024-10-11 · Michael H. Freedman

Kolmogorov and Arnold, in answering Hilbert's 13th problem (in the context of continuous functions), laid the foundations for the modern theory of Neural Networks (NNs). Their proof divides the representation of a multivariate function into two steps: The first (non-linear) inter-layer map gives a universal embedding of the data manifold into a single hidden layer whose image is patterned in such a way that a subsequent dynamic can then be defined to solve for the second inter-layer map. I interpret this pattern as "minor concentration" of the almost everywhere defined Jacobians of the interlayer map. Minor concentration amounts to sparsity for higher exterior powers of the Jacobians. We present a conceptual argument for how such sparsity may set the stage for the emergence of successively higher order concepts in today's deep NNs and suggest two classes of experiments to test this hypothesis.

📄 PDF Abstract BibTeX arXiv:2410.08451

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Kolmogorov-Arnold Networks are Radial Basis Function Networks

2024-05-10 · Ziyao Li

This short paper is a fast proof-of-concept that the 3-order B-splines used in Kolmogorov-Arnold Networks (KANs) can be well approximated by Gaussian radial basis functions. Doing so leads to FastKAN, a much faster imple…

Kolmogorov-Arnold Networks

Error bounds for deep ReLU networks using the Kolmogorov--Arnold superposition theorem

2019-06-27 · Hadrien Montanelli, Haizhao Yang

We prove a theorem concerning the approximation of multivariate functions by deep ReLU networks, for which the curse of the dimensionality is lessened. Our theorem is based on a constructive proof of the Kolmogorov--Arno…

Sinusoidal Approximation Theorem for Kolmogorov-Arnold Networks

2025-08-01 · Sergei Gleyzer, Hanh Nguyen, Dinesh P. Ramakrishnan, Eric A. F. Reinhardt arxiv

The Kolmogorov-Arnold representation theorem states that any continuous multivariable function can be exactly represented as a finite superposition of continuous single variable functions. Subsequent simplifications of t…

KAT to KANs: A Review of Kolmogorov-Arnold Networks and the Neural Leap Forward

2024-11-15 · Divesh Basina, Joseph Raj Vishal, Aarya Choudhary, Bharatesh Chakravarthi

The curse of dimensionality poses a significant challenge to modern multilayer perceptron-based architectures, often causing performance stagnation and scalability issues. Addressing this limitation typically requires va…

Kolmogorov-Arnold Networks

The Kolmogorov-Arnold representation theorem revisited

2020-07-31 · Johannes Schmidt-Hieber

There is a longstanding debate whether the Kolmogorov-Arnold representation theorem can explain the use of more than one hidden layer in neural networks. The Kolmogorov-Arnold representation decomposes a multivariate fun…