English
Related papers

Related papers: Extracting Formulae in Many-Valued Logic from Deep…

200 papers

We study lifted weight learning of Markov logic networks. We show that there is an algorithm for maximum-likelihood learning of 2-variable Markov logic networks which runs in time polynomial in the domain size. Our results are based on…

Artificial Intelligence · Computer Science 2019-03-08 Ondrej Kuzelka , Vyacheslav Kungurtsev

Interpretability is crucial for ensuring RL systems align with human values. However, it remains challenging to achieve in complex decision making domains. Existing methods frequently attempt interpretability at the level of fundamental…

Machine Learning · Computer Science 2025-06-03 Anna Soligo , Pietro Ferraro , David Boyle

We prove a large deviation principle for deep neural networks with Gaussian weights and at most linearly growing activation functions, such as ReLU. This generalises earlier work, in which bounded and continuous activation functions were…

Machine Learning · Statistics 2026-02-10 Quirin Vogel

Motivated by the interpretability question in ML models as a crucial element for the successful deployment of AI systems, this paper focuses on rule extraction as a means for neural networks interpretability. Through a systematic literature…

Machine Learning · Computer Science 2023-12-21 Sara El Mekkaoui , Loubna Benabbou , Abdelaziz Berrado

Activation function is crucial to the recent successes of deep neural networks. In this paper, we first propose a new activation function, Multiple Parametric Exponential Linear Units (MPELU), aiming to generalize and unify the rectified…

Computer Vision and Pattern Recognition · Computer Science 2017-01-18 Yang Li , Chunxiao Fan , Yong Li , Qiong Wu , Yue Ming

This paper aims to interpret the mechanism of feedforward ReLU networks by exploring their solutions for piecewise linear functions, through the deduction from basic rules. The constructed solution should be universal enough to explain some…

Machine Learning · Computer Science 2022-11-15 Changcun Huang

Neural networks are becoming a popular tool for solving many real-world problems such as object recognition and machine translation, thanks to its exceptional performance as an end-to-end solution. However, neural networks are complex…

Machine Learning · Computer Science 2020-09-29 Guoliang Dong , Jingyi Wang , Jun Sun , Yang Zhang , Xinyu Wang , Ting Dai , Jin Song Dong , Xingen Wang

This paper is an attempt to bridge the gap between deep learning and grammatical inference. Indeed, it provides an algorithm to extract a (stochastic) formal language from any recurrent neural network trained for language modelling. In…

Machine Learning · Computer Science 2020-09-29 Remi Eyraud , Stephane Ayache

We study \L ukasiewicz logic enriched with a scalar multiplication with scalars taken in $[0,1]$. Its algebraic models, called {\em Riesz MV-algebras}, are, up to isomorphism, unit intervals of Riesz spaces with a strong unit endowed with…

Logic · Mathematics 2017-09-26 Antonio Di Nola , Serafina Lapenta , Ioana Leustean

Neural networks are a fundamental aspect of modern artificial intelligence, playing a key role in various important machine learning architectures including transformers and graph neural networks. Recently, logical characterisations have…

Logic in Computer Science · Computer Science 2026-05-06 Damian Heiman , Antti Kuusisto , Esko Turunen

We propose another interpretation of well-known derivatives computations from regular expressions, due to Brzozowski, Antimirov or Lombardy and Sakarovitch, in order to abstract the underlying data structures (e.g. sets or linear…

Formal Languages and Automata Theory · Computer Science 2023-01-31 Samira Attou , Ludovic Mignot , Clément Miklarz , Florent Nicart

We propose another interpretation of well-known derivatives computations from regular expressions, due to Brzozowski, Antimirov or Lombardy and Sakarovitch, in order to abstract the underlying data structures (e.g. sets or linear…

Formal Languages and Automata Theory · Computer Science 2022-09-01 Samira Attou , Ludovic Mignot , Clément Miklarz , Florent Nicart

Traditional neural networks have an impressive classification performance, but what they learn cannot be inspected, verified or extracted. Neural Logic Networks on the other hand have an interpretable structure that enables them to learn a…

Machine Learning · Computer Science 2026-01-26 Vincent Perreault , Katsumi Inoue , Richard Labib , Alain Hertz

We propose a novel framework that leverages large language models (LLMs) to guide the rank selection in tensor network models for higher-order data analysis. By utilising the intrinsic reasoning capabilities and domain knowledge of LLMs,…

Machine Learning · Computer Science 2024-10-15 Giorgos Iacovides , Wuyang Zhou , Danilo Mandic

The deep neural networks (DNNs) have achieved great success in learning complex patterns with strong predictive power, but they are often thought of as "black box" models without a sufficient level of transparency and interpretability. It…

Machine Learning · Computer Science 2020-11-10 Agus Sudjianto , William Knauth , Rahul Singh , Zebin Yang , Aijun Zhang

Reverse engineering deep ReLU networks is a critical problem in understanding the complex behavior and interpretability of neural networks. In this research, we present a novel method for reconstructing deep ReLU networks by leveraging…

Machine Learning · Computer Science 2023-12-11 Mehrab Hamidi

We consider the embedding of piecewise-linear deep neural networks (ReLU networks) as surrogate models in mixed-integer linear programming (MILP) problems. A MILP formulation of ReLU networks has recently been applied by many authors to…

Optimization and Control · Mathematics 2022-01-10 Bjarne Grimstad , Henrik Andersson

Despite the highest classification accuracy in wide varieties of application areas, artificial neural network has one disadvantage. The way this Network comes to a decision is not easily comprehensible. The lack of explanation ability…

Computer Vision and Pattern Recognition · Computer Science 2016-10-18 Tameru Hailesilassie

This paper studies properties of the logic BV, which is an extension of multiplicative linear logic (MLL) with a self-dual non-commutative operator. BV is presented in the calculus of structures, a proof theoretic formalism that supports…

Logic in Computer Science · Computer Science 2017-01-11 Alwen Tiu

We present strong mixed-integer programming (MIP) formulations for high-dimensional piecewise linear functions that correspond to trained neural networks. These formulations can be used for a number of important tasks, such as verifying…

Optimization and Control · Mathematics 2020-01-23 Ross Anderson , Joey Huchette , Will Ma , Christian Tjandraatmadja , Juan Pablo Vielma