paper-with-me

Papers

Any Deep ReLU Network is Shallow

2023-06-20 · Mattia Jacopo Villani, Nandi Schoots

We constructively prove that every deep ReLU network can be rewritten as a functionally identical three-layer network with weights valued in the extended reals. Based on this proof, we provide an algorithm that, given a deep ReLU network, finds the explicit weights of the corresponding shallow network. The resulting shallow network is transparent and used to generate explanations of the model s behaviour.

📄 PDF Abstract BibTeX arXiv:2306.11827

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inference

2023-04-26 · Souvik Kundu, Yuke Zhang, Dake Chen, Peter A. Beerel

Large number of ReLU and MAC operations of Deep neural networks make them ill-suited for latency and compute-efficient private inference. In this paper, we present a model optimization method that allows a model to learn…

Model OptimizationSensitivity

Optimal rates of approximation by shallow ReLU$^k$ neural networks and applications to nonparametric regression

2023-04-04 · Yunfei Yang, Ding-Xuan Zhou

We study the approximation capacity of some variation spaces corresponding to shallow ReLU$^k$ neural networks. It is shown that sufficiently smooth functions are contained in these spaces with finite variation norms. Fo…

regression

Approximation capabilities of neural networks on unbounded domains

2019-10-21 · Ming-Xi Wang, Yang Qu

In this paper, we prove that a shallow neural network with a monotone sigmoid, ReLU, ELU, Softplus, or LeakyReLU activation function can arbitrarily well approximate any L^p(p>=2) integrable functions defined on R*[0,1]^…

On the Expressive Power of Neural Networks

2023-05-31 · Jan Holstermann

In 1989 George Cybenko proved in a landmark paper that wide shallow neural networks can approximate arbitrary continuous functions on a compact set. This universal approximation theorem sparked a lot of follow-up researc…

Equidistribution-based training of Free Knot Splines and ReLU Neural Networks

2024-07-02 · Simone Appella, Simon Arridge, Chris Budd, Teo Deveney 외

We consider the problem of univariate nonlinear function approximation using shallow neural networks (NN) with a rectified linear unit (ReLU) activation function. We show that the $L_2$ based approximation problem is ill…