Paper ID: 2407.02700

Output Range Analysis for Deep Neural Networks based on Simulated Annealing Processes

Helder Rojas, Nilton Rojas, Espinoza J. B., Luis Huamanchumo

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).

Submitted: Jul 2, 2024