3 papers
cs.LG2025
Tighter Truncated Rectangular Prism Approximation for RNN Robustness Verification
Xingqi Lin, Liangyu Chen, Min Wu +2
Robustness verification is a promising technique for rigorously proving Recurrent Neural Networks (RNNs) robustly. A key challenge is to over-approximate the nonlinear activation f…
cs.LG2025
IDInit: A Universal and Stable Initialization Method for Neural Network Training
Yu Pan, Chaozheng Wang, Zekai Wu +3
Deep neural networks have achieved remarkable accomplishments in practice. The success of these networks hinges on effective initialization methods, which are vital for ensuring st…
cs.AI2024
Marabou 2.0: A Versatile Formal Analyzer of Neural Networks
Haoze Wu, Omri Isac, Aleksandar Zeljić +14
This paper serves as a comprehensive system description of version 2.0 of the Marabou framework for formal analysis of neural networks. We discuss the tool's architectural design a…