paper-with-me

홈 › Papers

BDD4BNN: A BDD-based Quantitative Analysis Framework for Binarized Neural Networks

2021-03-12 · Yedi Zhang, Zhe Zhao, Guangke Chen, Fu Song, Taolue Chen

Verifying and explaining the behavior of neural networks is becoming increasingly important, especially when they are deployed in safety-critical applications. In this paper, we study verification problems for Binarized Neural Networks (BNNs), the 1-bit quantization of general real-numbered neural networks. Our approach is to encode BNNs into Binary Decision Diagrams (BDDs), which is done by exploiting the internal structure of the BNNs. In particular, we translate the input-output relation of blocks in BNNs to cardinality constraints which are then encoded by BDDs. Based on the encoding, we develop a quantitative verification framework for BNNs where precise and comprehensive analysis of BNNs can be performed. We demonstrate the application of our framework by providing quantitative robustness analysis and interpretability for BNNs. We implement a prototype tool BDD4BNN and carry out extensive experiments which confirm the effectiveness and efficiency of our approach.

📄 PDF Abstract BibTeX arXiv:2103.07224

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Similar Papers 제목 키워드 기반

BDC-Occ: Binarized Deep Convolution Unit For Binarized Occupancy Network

2024-05-27 · Zongkai Zhang, Zidong Xu, Wenming Yang, Qingmin Liao 외

Existing 3D occupancy networks demand significant hardware resources, hindering the deployment of edge devices. Binarized Neural Networks (BNN) offer substantially reduced computational and memory requirements. However, …

Binarization

Quantitative Verification of Neural Networks And its Security Applications

2019-06-25 · Teodora Baluta, Shiqi Shen, Shweta Shinde, Kuldeep S. Meel 외

Neural networks are increasingly employed in safety-critical domains. This has prompted interest in verifying or certifying logically encoded properties of neural networks. Prior work has largely focused on checking exis…

Fairness

Binarized Spectral Compressive Imaging

2023-05-17 · NeurIPS 2023 11 · Yuanhao Cai, Yuxin Zheng, Jing Lin, Xin Yuan 외

Existing deep learning models for hyperspectral image (HSI) reconstruction achieve good performance but require powerful hardwares with enormous memory and computational resources. Consequently, these methods can hardly …

Binarization

Efficient Super Resolution Using Binarized Neural Network

2018-12-16 · Yinglan Ma, Hongyu Xiong, Zhe Hu, Lizhuang Ma

Deep convolutional neural networks (DCNNs) have recently demonstrated high-quality results in single-image super-resolution (SR). DCNNs often suffer from over-parametrization and large amounts of redundancy, which result…

Binarizationimage-classificationImage ClassificationImage Enhancement+3

Taming Binarized Neural Networks and Mixed-Integer Programs

2023-10-05 · Johannes Aspman, Georgios Korpas, Jakub Marecek

There has been a great deal of recent interest in binarized neural networks, especially because of their explainability. At the same time, automatic differentiation algorithms such as backpropagation fail for binarized n…