神经网络验证（讲义） / Verification of Neural Networks (Lecture Notes)
1️⃣ 一句话总结
本文从理论角度系统介绍了如何验证前馈神经网络、循环神经网络以及 Transformer 等现代模型的正确性与安全性，涵盖相关规范语言与算法验证技术，帮助读者理解如何确保 AI 系统的可靠运行。
arXiv 提交日期: 2026-04-28
Abstract - Verification of Neural Networks (Lecture Notes)
These lecture notes provide an introduction to the verification of neural networks from a theoretical perspective. We discuss feed-forward neural networks, recurrent neural networks, attention mechanisms, and transformers, together with specification languages and algorithmic verification techniques.
源自 arXiv: 2604.25733