English
Related papers

Related papers: Computable functors and effective interpretability

200 papers

Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of…

Machine Learning · Computer Science 2025-03-17 Theodora-Mara Pîslar , Sara Magliacane , Atticus Geiger

The complexity of equivalence relations has received much attention in the recent literature. The main tool for such endeavour is the following reducibility: given equivalence relations $R$ and $S$ on natural numbers, $R$ is computably…

Logic · Mathematics 2023-11-09 Nikolay Bazhenov , Keng Meng Ng , Luca San Mauro , Andrea Sorbi

Many text classification applications require models with satisfying performance as well as good interpretability. Traditional machine learning methods are easy to interpret but have low accuracies. The development of deep learning models…

Computation and Language · Computer Science 2020-06-02 Zhengyang Wang , Xia Hu , Shuiwang Ji

In this article I propose an approach for defining replicability for prediction rules. Motivated by a recent NAS report, I start from the perspective that replicability is obtaining consistent results across studies suitable to address the…

Methodology · Statistics 2023-05-03 Giovanni Parmigiani

We define the syntax and reduction relation of a recursively typed lambda calculus with a parallel case-function (a parallel conditional). The reduction is shown to be confluent. We interpret the recursive types as information systems in a…

Logic in Computer Science · Computer Science 2008-06-12 Fritz Müller

We explore several concepts for analyzing the intuitive notion of computational irreducibility and we propose a robust formal definition, first in the field of cellular automata and then in the general field of any computable function f…

Computational Complexity · Computer Science 2012-02-06 Herve Zwirn , Jean-Paul Delahaye

The notion of computable reducibility between equivalence relations on the natural numbers provides a natural computable analogue of Borel reducibility. We investigate the computable reducibility hierarchy, comparing and contrasting it with…

Logic · Mathematics 2019-02-06 Samuel Coskey , Joel David Hamkins , Russell Miller

With machine learning models being increasingly used to aid decision making even in high-stakes domains, there has been a growing interest in developing interpretable models. Although many supposedly interpretable models have been proposed,…

Artificial Intelligence · Computer Science 2021-08-17 Forough Poursabzi-Sangdeh , Daniel G. Goldstein , Jake M. Hofman , Jennifer Wortman Vaughan , Hanna Wallach

This paper presents our implemented computational model for interpreting and generating indirect answers to Yes-No questions. Its main features are 1) a discourse-plan-based approach to implicature, 2) a reversible architecture for…

cmp-lg · Computer Science 2008-02-03 Nancy Green , Sandra Carberry

In previous papers on this project a general static logical framework for formalizing and mechanizing set theories of different strength was suggested, and the power of some predicatively acceptable theories in that framework was explored.…

Logic in Computer Science · Computer Science 2023-06-22 Arnon Avron , Liron Cohen

We characterize when a subfactor $N\subseteq M$ is oracle computable relative to a presentation of the ambient factor $M$ in terms of computability of the Jones basic construction, in terms of computable Pismner-Popa bases, and in terms of…

Logic · Mathematics 2024-09-30 Alec Fox , Isaac Goldbring

We study computably enumerable equivalence relations (ceers) on N and unravel a rich structural theory for a strong notion of reducibility among ceers.

Logic · Mathematics 2010-12-07 Su Gao , Peter Gerdes

The theory of computational complexity is used to underpin a recent model of neocortical sensory processing. We argue that encoding into reconstruction networks is appealing for communicating agents using Hebbian learning and working on…

Neurons and Cognition · Quantitative Biology 2007-05-23 Andras Lorincz

We propose using mechanistic interpretability -- techniques for reverse engineering model weights into human-interpretable algorithms -- to derive and compactly prove formal guarantees on model performance. We prototype this approach by…

Machine Learning · Computer Science 2024-12-25 Jason Gross , Rajashree Agrawal , Thomas Kwa , Euan Ong , Chun Hei Yip , Alex Gibson , Soufiane Noubir , Lawrence Chan

We introduce an operational rewriting-based semantics for strictly positive nested higher-order (co)inductive types. The semantics takes into account the "limits" of infinite reduction sequences. This may be seen as a refinement and…

Logic in Computer Science · Computer Science 2023-06-22 Łukasz Czajka

Mechanistic Interpretability aims to understand neural networks through causal explanations. We argue for the Explanatory View Hypothesis: that Mechanistic Interpretability research is a principled approach to understanding models because…

Machine Learning · Computer Science 2025-05-05 Kola Ayonrinde , Louis Jaburi

With the growing pervasiveness of artificial intelligence, the ability to explain the inferences made by machine learning models has become increasingly important. Numerous techniques for model explainability have been proposed, with…

Human-Computer Interaction · Computer Science 2026-04-08 Nicola Rossberg , Bennett Kleinberg , Barry O'Sullivan , Luca Longo , Andrea Visentin

When quantitative models are used to support decision-making on complex and important topics, understanding a model's ``reasoning'' can increase trust in its predictions, expose hidden biases, or reduce vulnerability to adversarial attacks.…

Machine Learning · Computer Science 2019-07-09 Dimitris Bertsimas , Arthur Delarue , Patrick Jaillet , Sebastien Martin

We often desire our models to be interpretable as well as accurate. Prior work on optimizing models for interpretability has relied on easy-to-quantify proxies for interpretability, such as sparsity or the number of operations required. In…

Machine Learning · Statistics 2018-11-01 Isaac Lage , Andrew Slavin Ross , Been Kim , Samuel J. Gershman , Finale Doshi-Velez

Extending G\"odel's \emph{Dialectica} interpretation, we provide a functional interpretation of classical theories of positive arithmetic inductive definitions, reducing them to theories of finite-type functionals defined using transfinite…

Logic · Mathematics 2009-02-17 Jeremy Avigad , Henry Towsner