English
Related papers

Related papers: Does resolving PvNP require a paradigm shift?

200 papers

As AI systems are used in high-stakes applications, ensuring interpretability is crucial. Mechanistic Interpretability (MI) aims to reverse-engineer neural networks by extracting human-understandable algorithms to explain their behavior.…

Machine Learning · Computer Science 2025-03-03 Maxime Méloux , Silviu Maniu , François Portet , Maxime Peyrard

If an active citizen should increasingly be a computationally enlightened one, replacing the autonomy of reason with the heteronomy of algorithms, then I argue in this article that we must begin teaching the principles of critiquing the…

Computers and Society · Computer Science 2025-05-19 David M. Berry

Sound deductive reasoning -- the ability to derive new knowledge from existing facts and rules -- is an indisputably desirable aspect of general intelligence. Despite the major advances of AI systems in areas such as math and science,…

Artificial Intelligence · Computer Science 2025-07-01 András György , Tor Lattimore , Nevena Lazić , Csaba Szepesvári

Explainable artificial intelligence techniques are developed at breakneck speed, but suitable evaluation approaches lag behind. With explainers becoming increasingly complex and a lack of consensus on how to assess their utility, it is…

Human-Computer Interaction · Computer Science 2023-04-18 Edward Small , Yueqing Xuan , Danula Hettiachchi , Kacper Sokol

Mathematical proofs are both paradigms of certainty and some of the most explicitly-justified arguments that we have in the cultural record. Their very explicitness, however, leads to a paradox, because the probability of error grows…

Symbolic Computation · Computer Science 2022-04-13 Scott Viteri , Simon DeDeo

Weighted knowledge bases for description logics with typicality under a "concept-wise" multi-preferential semantics provide a logical interpretation of MultiLayer Perceptrons. In this context, Answer Set Programming (ASP) has been shown to…

Artificial Intelligence · Computer Science 2023-03-28 Mario Alviano , Laura Giordano , Daniele Theseider Dupré

Although whether P equals NP is an important, open problem in computer science, and although Jaeger's 2008 paper, "Solving the P/NP Problem Under Intrinsic Uncertainty" (arXiv:0811.0463) presents an attempt at tackling the problem by…

Computational Complexity · Computer Science 2009-04-27 Andrew Keenan Richardson , Cole Arthur Brown

Explaining black-box Artificial Intelligence (AI) models is a cornerstone for trustworthy AI and a prerequisite for its use in safety critical applications such that AI models can reliably assist humans in critical decisions. However,…

Computer Vision and Pattern Recognition · Computer Science 2023-03-10 Poulami Sinhamahapatra , Lena Heidemann , Maureen Monnet , Karsten Roscher

Agents' judgment depends on perception and previous knowledge. Assuming that previous knowledge depends on perception, we can say that judgment depends on perception. So, if judgment depends on perception, can agents judge that they have…

Neurons and Cognition · Quantitative Biology 2012-02-21 Ahmed M. Mahran

Automated mathematical reasoning is a challenging problem that requires an agent to learn algebraic patterns that contain long-range dependencies. Two particular tasks that test this type of reasoning are (1) mathematical equation…

Machine Learning · Computer Science 2021-04-08 Ankur Mali , Alexander Ororbia , Daniel Kifer , C. Lee Giles

In spite of several claims stating that some models are more interpretable than others -- e.g., "linear models are more interpretable than deep neural networks" -- we still lack a principled notion of interpretability to formally compare…

Artificial Intelligence · Computer Science 2020-11-16 Pablo Barceló , Mikaël Monet , Jorge Pérez , Bernardo Subercaseaux

Probabilistic automata are an extension of nondeterministic finite automata in which transitions are annotated with probabilities. Despite its simplicity, this model is very expressive and many of the associated algorithmic questions are…

Formal Languages and Automata Theory · Computer Science 2022-05-20 Nathanaël Fijalkow , Cristian Riveros , James Worrell

Neural networks are growing more capable on their own, but we do not understand their neural mechanisms. Understanding these mechanisms' decision-making processes, or mechanistic interpretability, enables (1) accountability and control in…

Computation and Language · Computer Science 2026-03-02 Mason Kadem , Rong Zheng

Interpretability provides a toolset for understanding how and why neural networks behave in certain ways. However, there is little unity in the field: most studies employ ad-hoc evaluations and do not share theoretical foundations, making…

We present a computable algorithm that assigns probabilities to every logical statement in a given formal language, and refines those probabilities over time. For instance, if the language is Peano arithmetic, it assigns probabilities to…

Artificial Intelligence · Computer Science 2020-12-09 Scott Garrabrant , Tsvi Benson-Tilsen , Andrew Critch , Nate Soares , Jessica Taylor

Attempts to replicate probabilistic reasoning in expert systems have typically overlooked a critical ingredient of that process. Probabilistic analysis typically requires extensive judgments regarding interdependencies among hypotheses and…

Artificial Intelligence · Computer Science 2013-04-15 Marvin S. Cohen

Over the past few years, insights from computer science, statistical physics, and information theory have revealed phase transitions in a wide array of high-dimensional statistical problems at two distinct thresholds: One is the…

Statistics Theory · Mathematics 2018-08-14 Yihong Wu , Jiaming Xu

Transparency, user trust, and human comprehension are popular ethical motivations for interpretable machine learning. In support of these goals, researchers evaluate model explanation performance using humans and real world applications.…

Artificial Intelligence · Computer Science 2019-10-31 Bernease Herman

Mechanistic Interpretability (MI) promises a path toward fully understanding how neural networks make their predictions. Prior work demonstrates that even when trained to perform simple arithmetic, models can implement a variety of…

Machine Learning · Computer Science 2024-05-28 Ouail Kitouni , Niklas Nolte , Víctor Samuel Pérez-Díaz , Sokratis Trifinopoulos , Mike Williams

Explainable models in Artificial Intelligence are often employed to ensure transparency and accountability of AI systems. The fidelity of the explanations are dependent upon the algorithms used as well as on the fidelity of the data. Many…

Machine Learning · Computer Science 2019-07-31 Muhammad Aurangzeb Ahmad , Carly Eckert , Ankur Teredesai