Deep learning has emerged as an effective approach for creating modern software systems,
with neural networks often surpassing hand-crafted systems. Unfortunately, neural networks …

A central quest in explainable AI relates to understanding the decisions made by (learned)
classifiers. There are three dimensions of this understanding that have been receiving …

Formal verification of neural networks is an active topic of research, and recent advances
have significantly increased the size of the networks that verification tools can handle …

Deep learning has become a promising programming paradigm in software development,
owing to its surprising performance in solving many challenging tasks. Deep neural …

Verifying and explaining the behavior of neural networks is becoming increasingly
important, especially when they are deployed in safety-critical applications. In this paper, we …

To alleviate the practical constraints for deploying deep neural networks (DNNs) on edge
devices, quantization is widely regarded as one promising technique. It reduces the …

Deploying neural networks (NNs) in low-resource domains is challenging because of their
high computing, memory, and power requirements. For this reason, NNs are often quantized …

Quantized deep neural networks (DNNs) have the potential to find wide applications in
safety-critical cyber–physical systems implemented on processors supporting only integer …

We introduce a novel approach to the automated termination analysis of computer
programs: we use neural networks to represent ranking functions. Ranking functions map …

Adversarial training (ie, training on adversarially perturbed input data) is a well-studied
method for making neural networks robust to potential adversarial attacks during inference …