The field of machine learning focuses on computationally efficient, yet approximate
algorithms. On the contrary, the field of formal methods focuses on mathematical rigor and …

In text classifier models, the complexity of recurrent neural networks (RNNs) is very high
because of the vast state space and uncertainty of transitions, which makes the RNN …

Reinforcement Learning represents a powerful paradigm in artificial intelligence, enabling
agents to learn optimal behaviors through interactions with their environment. However …

This work studies the question of learning probabilistic deterministic automata from
language models. For this purpose, it focuses on analyzing the relations defined on …

In this paper, we present the envisioned style and scope of the new topic “Explanation
Paradigms Leveraging Analytic Intuition”(ExPLAIn) with the International Journal on …

This paper introduces Malwa, a web-based tool implementing our new method of
learnability by design that is designed to significantly reduce the main entry hurdle, the …

This work tackles the general problem of verifying the behavior of sequence processing
neural networks, specifically neural acceptors and neural language models. The …

Verification of Neural Networks Page 1 Verification of Neural Networks Lecture Notes (in
progress) Benedikt Bollig Université Paris-Saclay, CNRS, ENS Paris-Saclay, LMF Gif-sur-Yvette …

The past decade has witnessed the rise of several intelligent systems fueled by the large-
scale adoption of data-driven techniques. However, due to the inherent black-box nature of …