2019/10/09 by Haakon Robinson, Adil Rasheed, Robinson, Haakon +3 · 1 citation
Computer Science · Mathematics · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Neural and Evolutionary Computing (cs.NE) #cs.LG #cs.NE #stat.ML
paper · pdf · doi:10.48550/arxiv.1910.03879
12 pages, 10 figures (not including bio pics), submitted to IEEE Transactions on Neural Networks and Learning Systems
openalex publication_date 2019/10/09 · arxiv created 2020/01/19 · arxiv updated 2020/01/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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 behaviour have raised concerns over their use in safety-critical applications. A first step to understanding these networks is to develop alternate representations that allow for further analysis. It has been shown that neural networks with piecewise affine activation functions are themselves piecewise affine, with their domains consisting of a vast number of linear regions. So far, the research on this topic has focused on counting the number of linear regions, rather than obtaining explicit piecewise affine representations. This work presents a novel algorithm that can compute the piecewise affine form of any fully connected neural network with rectified linear unit activations.