paper-with-me

홈 › Papers

Verification of Binarized Neural Networks via Inter-Neuron Factoring

2017-10-09 · Chih-Hong Cheng, Georg Nührenberg, Chung-Hao Huang, Harald Ruess

We study the problem of formal verification of Binarized Neural Networks (BNN), which have recently been proposed as a energy-efficient alternative to traditional learning networks. The verification of BNNs, using the reduction to hardware verification, can be even more scalable by factoring computations among neurons within the same layer. By proving the NP-hardness of finding optimal factoring as well as the hardness of PTAS approximability, we design polynomial-time search heuristics to generate factoring solutions. The overall framework allows applying verification techniques to moderately-sized BNNs for embedded devices with thousands of neurons and inputs.

📄 PDF Abstract BibTeX arXiv:1710.03107

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Refactoring Neural Networks for Verification

2019-08-06 · David Shriver, Dong Xu, Sebastian Elbaum, Matthew B. Dwyer

Deep neural networks (DNN) are growing in capability and applicability. Their effectiveness has led to their use in safety critical and autonomous systems, yet there is a dearth of cost-effective methods available for re…

An SMT-Based Approach for Verifying Binarized Neural Networks

2020-11-05 · Guy Amir, Haoze Wu, Clark Barrett, Guy Katz

Deep learning has emerged as an effective approach for creating modern software systems, with neural networks often surpassing hand-crafted systems. Unfortunately, neural networks are known to suffer from various safety …

A Sugeno Integral View of Binarized Neural Network Inference

2026-04-20 · Ismaïl Baaj, Henri Prade arxiv

In this article, we establish a precise connection between binarized neural networks (BNNs) and Sugeno integrals. The advantage of the Sugeno integral is that it provides a framework for representing the importance of in…

The fine line between dead neurons and sparsity in binarized spiking neural networks

2022-01-28 · Jason K. Eshraghian, Wei D. Lu

Spiking neural networks can compensate for quantization error by encoding information either in the temporal domain, or by processing discretized quantities in hidden states of higher precision. In theory, a wide dynamic…

Quantization

Neural Network Verification as Piecewise Linear Optimization: Formulations for the Composition of Staircase Functions

2022-11-27 · Tu Anh-Nguyen, Joey Huchette

We present a technique for neural network verification using mixed-integer programming (MIP) formulations. We derive a \emph{strong formulation} for each neuron in a network using piecewise linear activation functions. A…