This paper tackles the challenging problem of output range estimation for Deep Neural Networks (DNNs), introducing a novel algorithm based on Simulated Annealing (SA). Our approach addresses the lack of local geometric information and high non-linearity in DNNs, making it versatile across various architectures, especially Residual Neural Networks (ResNets). We present a straightforward, implementation-friendly algorithm that avoids restrictive assumptions about network architecture. Through theoretical analysis and experimental evaluations, including tests on the Ackley function, we demonstrate our algorithm's effectiveness in navigating complex, non-convex surfaces and accurately estimating DNN output ranges. Futhermore, the Python codes of this experimental evaluation that support our results are available in our GitHub repository (https://github.com/Nicerova7/output-range-analysis-for-deep-neural-networks-with-simulated-annealing).

翻译：本文解决了深度神经网络输出范围估计这一具有挑战性的问题，引入了一种基于模拟退火的新型算法。我们的方法针对DNN中局部几何信息缺失和高非线性问题，使其能够适用于各种架构，尤其是残差神经网络。我们提出了一种简单、易于实现的算法，避免了对网络架构的严格假设。通过理论分析和实验评估，包括在Ackley函数上的测试，我们证明了该算法在探索复杂非凸曲面和准确估计DNN输出范围方面的有效性。此外，支持我们结果的实验评估Python代码已在我们的GitHub仓库中开源（https://github.com/Nicerova7/output-range-analysis-for-deep-neural-networks-with-simulated-annealing）。