English
Related papers

Related papers: Guaranteed Optimal Compositional Explanations for …

200 papers

Decisions in organizations are about evaluating alternatives and choosing the one that would best serve organizational goals. To the extent that the evaluation of alternatives could be formulated as a predictive task with appropriate…

Human-Computer Interaction · Computer Science 2022-06-30 Charles Wan , Rodrigo Belo , Leid Zejnilović

This article introduces the idea that probabilistic reasoning (PR) may be understood as "information compression by multiple alignment, unification and search" (ICMAUS). In this context, multiple alignment has a meaning which is similar to…

Artificial Intelligence · Computer Science 2007-05-23 J Gerard Wolff

Although neural sequence-to-sequence models have been successfully applied to semantic parsing, they fail at compositional generalization, i.e., they are unable to systematically generalize to unseen compositions of seen components.…

Computation and Language · Computer Science 2021-09-10 Hao Zheng , Mirella Lapata

Vision-language models (VLMs) transform environment percepts into vision-language semantics interpretable by LLMs. However, completing complex tasks often requires reasoning about information beyond what is currently perceived. We propose…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Robin Karlsson , Francisco Lepe-Salazar , Kazuya Takeda

The recent success of deep learning models in solving complex problems and in different domains has increased interest in understanding what they learn. Therefore, different approaches have been employed to explain these models, one of…

Machine Learning · Computer Science 2021-10-29 Sayo M. Makinwa , Biagio La Rosa , Roberto Capobianco

We present a new method for scaling automatic configuration of computer networks. The key idea is to relax the computationally hard search problem of finding a configuration that satisfies a given specification into an approximate objective…

Networking and Internet Architecture · Computer Science 2022-11-04 Luca Beurer-Kellner , Martin Vechev , Laurent Vanbever , Petar Veličković

Understanding brain function, constructing computational models and engineering neural prosthetics require assessing two problems, namely encoding and decoding, but their relation remains controversial. For decades, the encoding problem has…

Neurons and Cognition · Quantitative Biology 2017-01-16 Hugo Gabriel Eyherabide

The generation of comprehensible explanations is an essential feature of modern artificial intelligence systems. In this work, we consider probabilistic logic programming, an extension of logic programming which can be useful to model…

Artificial Intelligence · Computer Science 2023-08-17 Germán Vidal

Beam search is the default decoding strategy for many sequence generation tasks in NLP. The set of approximate K-best items returned by the algorithm is a useful summary of the distribution for many applications; however, the candidates…

Computation and Language · Computer Science 2023-03-03 Clara Meister , Afra Amini , Tim Vieira , Ryan Cotterell

The theory of optimal transportation has developed into a powerful and elegant framework for comparing probability distributions, with wide-ranging applications in all areas of science. The fundamental idea of analyzing probabilities by…

Methodology · Statistics 2025-03-14 Florian F Gunsilius

Various non-trivial spaces are becoming popular for embedding structured data such as graphs, texts, or images. Following spherical and hyperbolic spaces, more general product spaces have been proposed. However, searching for the best…

Machine Learning · Computer Science 2022-04-11 Kirill Shevkunov , Liudmila Prokhorenkova

In recent years, there has been an increased need for the use of active systems - systems required to act automatically based on events, or changes in the environment. Such systems span many areas, from active databases to applications that…

Artificial Intelligence · Computer Science 2012-07-09 Segev Wasserkrug , Avigdor Gal , Opher Etzion

Among the various forms of reasoning studied in the context of artificial intelligence, qualitative reasoning makes it possible to infer new knowledge in the context of imprecise, incomplete information without numerical values. In this…

Artificial Intelligence · Computer Science 2026-02-10 Quentin Cohen-Solal , Alexandre Niveau , Maroua Bouzid

The optimal selection of experimental conditions is essential to maximizing the value of data for inference and prediction, particularly in situations where experiments are time-consuming and expensive to conduct. We propose a general…

Machine Learning · Statistics 2012-12-04 Xun Huan , Youssef M. Marzouk

This paper addresses the generation of explanations with visual examples. Given an input sample, we build a system that not only classifies it to a specific category, but also outputs linguistic explanations and a set of visual examples…

Computer Vision and Pattern Recognition · Computer Science 2019-05-21 Atsushi Kanehira , Tatsuya Harada

Modelling musical structure is vital yet challenging for artificial intelligence systems that generate symbolic music compositions. This literature review dissects the evolution of techniques for incorporating coherent structure, from…

Sound · Computer Science 2024-03-14 Keshav Bhandari , Simon Colton

In this article, we present a leap-forward expansion to the study of explainability in neural networks by considering explanations as answers to abstract reasoning-based questions. With $P$ as the prediction from a neural network, these…

Machine Learning · Computer Science 2022-02-25 Ghassan AlRegib , Mohit Prabhushankar

This paper describes a process for combining patterns and features, to guide a search process and make predictions. It is based on the functionality that a human brain might have, which is a highly distributed network of simple neuronal…

Artificial Intelligence · Computer Science 2021-01-05 Kieran Greer

Neuron identification is a popular tool in mechanistic interpretability, aiming to uncover the human-interpretable concepts represented by individual neurons in deep networks. While algorithms such as Network Dissection and CLIP-Dissect…

Artificial Intelligence · Computer Science 2025-12-23 Ge Yan , Tuomas Oikarinen , Tsui-Wei , Weng

We propose a new interpretability method for neural networks, which is based on a novel mathematico-philosophical theory of reasons. Our method computes a vector for each neuron, called its reasons vector. We then can compute how strongly…

Machine Learning · Computer Science 2025-05-21 Levin Hornischer , Hannes Leitgeb