English
Related papers

Related papers: Investigating Concept Alignment Using Implausible …

200 papers

Deep Learning has already been successfully applied to analyze industrial sensor data in a variety of relevant use cases. However, the opaque nature of many well-performing methods poses a major obstacle for real-world deployment.…

Machine Learning · Computer Science 2023-10-20 Thomas Decker , Michael Lebacher , Volker Tresp

Modern AI models contain much of human knowledge, yet understanding of their internal representation of this knowledge remains elusive. Characterizing the structure and properties of this representation will lead to improvements in model…

Computation and Language · Computer Science 2025-05-30 Daniel Beaglehole , Adityanarayanan Radhakrishnan , Enric Boix-Adserà , Mikhail Belkin

Reasoning about objects, relations, and physics is central to human intelligence, and a key goal of artificial intelligence. Here we introduce the interaction network, a model which can reason about how objects in complex systems interact,…

Artificial Intelligence · Computer Science 2016-12-02 Peter W. Battaglia , Razvan Pascanu , Matthew Lai , Danilo Rezende , Koray Kavukcuoglu

With the availability of large databases and recent improvements in deep learning methodology, the performance of AI systems is reaching or even exceeding the human level on an increasing number of complex tasks. Impressive examples of this…

Artificial Intelligence · Computer Science 2017-08-29 Wojciech Samek , Thomas Wiegand , Klaus-Robert Müller

Large language models (LLMs) are often portrayed as merely imitating linguistic patterns without genuine understanding. We argue that recent findings in mechanistic interpretability (MI), the emerging field probing the inner workings of…

Computation and Language · Computer Science 2026-02-26 Pierre Beckmann , Matthieu Queloz

Do AI systems truly understand human concepts or merely mimic surface patterns? We investigate this through chess, where human creativity meets precise strategic concepts. Analyzing a 270M-parameter transformer that achieves…

Machine Learning · Computer Science 2025-11-05 Semyon Lomasov , Judah Goldfeder , Mehmet Hamza Erol , Matthew So , Yao Yan , Addison Howard , Nathan Kutz , Ravid Shwartz Ziv

High-level reasoning can be defined as the capability to generalize over knowledge acquired via experience, and to exhibit robust behavior in novel situations. Such form of reasoning is a basic skill in humans, who seamlessly use it in a…

Artificial Intelligence · Computer Science 2023-11-15 Alessandro Oltramari

This paper presents a novel concept learning framework for enhancing model interpretability and performance in visual classification tasks. Our approach appends an unsupervised explanation generator to the primary classifier network and…

Computer Vision and Pattern Recognition · Computer Science 2024-04-04 Tanmay Garg , Deepika Vemuri , Vineeth N Balasubramanian

We define and study the problem of modular concept learning, that is, learning a concept that is a cross product of component concepts. If an element's membership in a concept depends solely on it's membership in the components, learning…

Machine Learning · Computer Science 2019-11-11 Benjamin Caulfield , Sanjit A. Seshia

Humans leverage compositionality to efficiently learn new concepts, understanding how familiar parts can combine together to form novel objects. In contrast, popular computer vision models struggle to make the same types of inferences,…

Computer Vision and Pattern Recognition · Computer Science 2023-06-01 Yanli Zhou , Reuben Feinman , Brenden M. Lake

An unsupervised shape analysis is proposed to learn concepts reflecting shape commonalities. Our approach is two-fold: i) a spatial topology analysis of point cloud segment constellations within objects is used in which constellations are…

Computer Vision and Pattern Recognition · Computer Science 2018-11-21 Christian A. Mueller , Andreas Birk

Visual object recognition -- the behavioral ability to rapidly and accurately categorize many visually encountered objects -- is core to primate cognition. This behavioral capability is algorithmically impressive because of the myriad…

Neurons and Cognition · Quantitative Biology 2023-12-12 Kohitij Kar , James J DiCarlo

From its inception, AI has had a rather ambivalent relationship with humans -- swinging between their augmentation and replacement. Now, as AI technologies enter our everyday lives at an ever increasing pace, there is a greater need for AI…

Artificial Intelligence · Computer Science 2024-05-28 Sarath Sreedharan , Anagha Kulkarni , Subbarao Kambhampati

As artificial intelligence systems become increasingly integrated into daily life, the field of explainability has gained significant attention. This trend is particularly driven by the complexity of modern AI models and their…

Computer Vision and Pattern Recognition · Computer Science 2025-01-22 Rémi Kazmierczak , Eloïse Berthier , Goran Frehse , Gianni Franchi

Evaluating explanations of image classifiers regarding ground truth, e.g. segmentation masks defined by human perception, primarily evaluates the quality of the models under consideration rather than the explanation methods themselves.…

Computer Vision and Pattern Recognition · Computer Science 2023-11-09 Hubert Baniecki , Maciej Chrabaszcz , Andreas Holzinger , Bastian Pfeifer , Anna Saranti , Przemyslaw Biecek

Neural network models are widely used in a variety of domains, often as black-box solutions, since they are not directly interpretable for humans. The field of explainable artificial intelligence aims at developing explanation methods to…

Machine Learning · Computer Science 2023-07-25 Patrik Hammersborg , Inga Strümke

AI alignment is often framed as the task of ensuring that an AI system follows a set of stated principles or human preferences, but general principles rarely determine their own application in concrete cases. When principles conflict, when…

Artificial Intelligence · Computer Science 2026-04-14 Behrooz Razeghi

Large Language Models (LLMs) are recruited in applications that span from clinical assistance and legal support to question answering and education. Their success in specialized tasks has led to the claim that they possess human-like…

Computation and Language · Computer Science 2024-07-10 Vittoria Dentella , Fritz Guenther , Elliot Murphy , Gary Marcus , Evelina Leivada

Interactive Artificial Intelligence (AI) agents are becoming increasingly prevalent in society. However, application of such systems without understanding them can be problematic. Black-box AI systems can lead to liability and…

Computers and Society · Computer Science 2023-01-16 Pradyumna Tambwekar , Matthew Gombolay

As semi-autonomous vehicles (AVs) become prevalent, drivers must collaborate with AI systems whose decision-making processes remain opaque. This study examines how drivers of AVs develop folk theories to interpret algorithmic behavior that…

Human-Computer Interaction · Computer Science 2026-02-10 Yehuda Perry , Tawfiq Ammari
‹ Prev 1 3 4 5 6 7 10 Next ›