paper-with-me

Papers

Formalizing Piecewise Affine Activation Functions of Neural Networks in Coq

2023-01-30 · Andrei Aleksandrov, Kim Völlinger

Verification of neural networks relies on activation functions being piecewise affine (pwa) -- enabling an encoding of the verification problem for theorem provers. In this paper, we present the first formalization of pwa activation functions for an interactive theorem prover tailored to verifying neural networks within Coq using the library Coquelicot for real analysis. As a proof-of-concept, we construct the popular pwa activation function ReLU. We integrate our formalization into a Coq model of neural networks, and devise a verified transformation from a neural network N to a pwa function representing N by composing pwa functions that we construct for each layer. This representation enables encodings for proof automation, e.g. Coq's tactic lra -- a decision procedure for linear real arithmetic. Further, our formalization paves the way for integrating Coq in frameworks of neural network verification as a fallback prover when automated proving fails.

📄 PDF Abstract BibTeX arXiv:2301.12893

Code (1)

verinncoq/formalizing-pwa 공식 구현

Methods 이 논문이 사용한 방법론

Library 설명 없음

Similar Papers 제목 키워드 기반

Expressivity Saturation: Reduced Affine Region Usage Under Increasing Task Complexity

2026-06-19 · Xuan Qi, Yi Wei, Fanqi Yu, Manuel Lecha arxiv

Piecewise-affine neural networks (e.g., with ReLU or LeakyReLU activations) implement continuous piecewise-affine maps, and the number of affine regions provides a natural proxy for expressive capacity. However, the gap …

Dissecting Deep Neural Networks

2019-10-09 · Haakon Robinson, Adil Rasheed, Omer San

In exchange for large quantities of data and processing power, deep neural networks have yielded models that provide state of the art predication capabilities in many fields. However, a lack of strong guarantees on their…

AffineLens: Capturing the Continuous Piecewise Affine Functions of Neural Networks

2026-05-07 · Yi Wei, Xuan Qi, Furao Shen, Jian Zhao 외 arxiv

Piecewise affine neural networks (PANNs) provide a principled geometric perspective on neural network expressivity by characterizing the input--output map as a continuous piecewise affine (CPA) function whose complexity …

Minimum width for universal approximation using squashable activation functions

2025-04-10 · Jonghyun Shin, Namjun Kim, Geonho Hwang, Sejun Park

The exact minimum width that allows for universal approximation of unbounded-depth networks is known only for ReLU and its variants. In this work, we study the minimum width of networks using general activation functions…

Optimized Piecewise Affine Abstractions of Neural Networks with Learnable Activation Functions

2026-02-06 · Noah Schwartz, Chandra Kanth Nagesh, Sriram Sankaranarayanan, Ramneet Kaur 외 arxiv

We present a generalized framework for the range verification of neural networks featuring non-linear activation functions. Our approach first constructs an ``optimized piecewise affine abstraction" of the network that r…

Gaussian Processes