Concept

Interpretability

In mathematical logic, interpretability is a relation between formal theories that expresses the possibility of interpreting or translating one into the other. Assume T and S are formal theories. Slightly simplified, T is said to be interpretable in S if and only if the language of T can be translated into the language of S in such a way that S proves the translation of every theorem of T. Of course, there are some natural conditions on admissible translations here, such as the necessity for a translation to preserve the logical structure of formulas. This concept, together with weak interpretability, was introduced by Alfred Tarski in 1953. Three other related concepts are cointerpretability, logical tolerance, and cotolerance, introduced by Giorgi Japaridze in 1992–93.

Official source

https://en.wikipedia.org/wiki/Interpretability

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related courses (3)

EE-556: Mathematics of data: from theory to computation

This course provides an overview of key advances in continuous optimization and statistical analysis for machine learning. We review recent learning formulations and models as well as their guarantees

MATH-111(e): Linear Algebra

L'objectif du cours est d'introduire les notions de base de l'algèbre linéaire et ses applications. ...

EE-411: Fundamentals of inference and learning

This is an introductory course in the theory of statistics, inference, and machine learning, with an emphasis on theoretical understanding & practical exercises. The course will combine, and alternate, between mathematical theoretical foundations and prac ...

Related lectures (32)

Machine Learning for Medicine: Insights and Interpretability

Explores the application of machine learning in medicine, emphasizing interpretability, variability between patients, and the quest for transparent equations in medical models.

Generative Modeling: Then, Now and Tomorrow?

Explores the evolution of generative modeling, from traditional methods to cutting-edge advancements, addressing challenges and envisioning future possibilities.

Mathematics of Data: Deep Learning Introduction

Covers a mathematical introduction to deep learning, including challenges, power of linear classifiers, model scaling, and theoretical aspects.

Related publications (4)

32 examples of LLM applications in materials science and chemistry: towards automation, assistants, agents, and accelerated scientific discovery

Large language models (LLMs) are reshaping many aspects of materials science and chemistry research, enabling advances in molecular property prediction, materials design, scientific automation, knowledge extraction, and more. Recent developments demonstrate that the latest class of models are able to integrate structured and unstructured data, assist in hypothesis generation, and streamline research workflows. To explore the frontier of LLM capabilities across the research lifecycle, we review applications

2025

One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models

For large language models (LLMs), sparse autoencoders (SAEs) have been shown to decompose intermediate representations that often are not interpretable directly into sparse sums of interpretable features, facilitating better control and subsequent analysis. However, similar analyses and approaches have been lacking for text-to- image models. We investigate the possibility of using SAEs to learn interpretable features for SDXL Turbo, a few-step text-to-image diffusion model. To this end, we train SAEs on the

Neural Information Processing Systems Foundation, Inc. (NeurIPS)2025

Universal differential equations for estimating terrestrial evaporation

Terrestrial evaporation (E) is an essential climate variable, linking water, energy and carbon cycles. As E is influenced by the state of the atmospheric boundary layer, vegetation and soil, its modelling is a complex task, resulting in a myriad of simulation approaches. To combine the strong predictive skills of data-driven models with the interpretability and physical consistency of process-based models (PBMs), a new research field of differentiable modelling has emerged1. Here, we present a differentiab

2025

Related concepts (1)

Interpretability logic

Interpretability logics comprise a family of modal logics that extend provability logic to describe interpretability or various related metamathematical properties and relations such as weak interpretability, Π1-conservativity, cointerpretability, tolerance, cotolerance, and arithmetic complexities. Main contributors to the field are Alessandro Berarducci, Petr Hájek, Konstantin Ignatiev, Giorgi Japaridze, Franco Montagna, Vladimir Shavrukov, Rineke Verbrugge, Albert Visser, and Domenico Zambella.

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Official source

https://en.wikipedia.org/wiki/Interpretability

About this result

Related courses (3)

EE-556: Mathematics of data: from theory to computation

MATH-111(e): Linear Algebra

L'objectif du cours est d'introduire les notions de base de l'algèbre linéaire et ses applications. ...

EE-411: Fundamentals of inference and learning

Related lectures (32)

Machine Learning for Medicine: Insights and Interpretability

Explores the application of machine learning in medicine, emphasizing interpretability, variability between patients, and the quest for transparent equations in medical models.

Generative Modeling: Then, Now and Tomorrow?

Explores the evolution of generative modeling, from traditional methods to cutting-edge advancements, addressing challenges and envisioning future possibilities.

Mathematics of Data: Deep Learning Introduction

Covers a mathematical introduction to deep learning, including challenges, power of linear classifiers, model scaling, and theoretical aspects.

Related publications (4)

32 examples of LLM applications in materials science and chemistry: towards automation, assistants, agents, and accelerated scientific discovery

2025

One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models

Neural Information Processing Systems Foundation, Inc. (NeurIPS)2025

Universal differential equations for estimating terrestrial evaporation

2025

Related people (6)

Alexandre Massoud Alahi

Alexandre Alahi is currently an Assistant Professor at EPFL. He spent five years at Stanford University as a Post-doc and Research Scientist after obtaining his Ph.D. from EPFL. His research enables machines to perceive the world and make decisions in the context of transportation problems and smart environments. He has worked on the theoretical challenges and practical applications of socially-aware Artificial Intelligence, i.e., systems equipped with perception and social intelligence. He was awarded the Swiss NSF early and advanced researcher grants for his work on predicting human social behavior. He won the CVPR Open Source Award (2012) for his work on Retina-inspired image descriptors, and the ICDSC Challenge Prize (2009) for his sparsity-driven algorithm that has tracked more than 100 million pedestrians to date. His research has been covered internationally by BBC, abc, PBS, Euronews, Wall street journal, and other national news outlets around the world. Alexandre has also co-founded multiple startups such as Visiosafe, and won several startup competitions. He was elected as one of the Top 20 Swiss Venture leaders in 2010.

Antoine Bosselut

Antoine Bosselut is an assistant professor at EPFL. He leads the EPFL NLP group, which conducts research on natural language processing (NLP) systems that can model, represent, and reason about human and world knowledge. Prior to joining EPFL, he was a postdoctoral researcher at Stanford University working in the SNAP and NLP groups and a young investigator on the Mosaic project at the Allen Institute for AI . He completed his PhD at the University of Washington.

Deniz Bayazit

Zeming Chen

Radhakrishna Achanta

Expertise Image Processing, Computer Vision, and Machine Learning Radhakrishna Achanta has a PhD in computer science from EPFL, an MSc from NUS, Singapore, and a BEng from India. He has over 20 years of industrial and academic experience in the capacities of an individual contributor as well as a manager. His domains of expertise are Computer Vision, Image Processing, and Machine Learning. He has authored over 50 peer reviewed papers and patents, which have more than 23’000 citations. He has co-founded 4 st

Andrea Cavallaro

Expertise I focus on machine learning for audio-visual sensing to enable systems to serve agreed purposes and improve their abilities through interactions with the environment, with other systems and with people. The goal of my research is to create the next-generation machine perception models for the effective use of sensory data, and the safe operation of autonomous systems that gain information about their environment and make decisions in partnership with humans or independently. These models are trans

Related concepts (1)

Interpretability logic

Related people (6)

Alexandre Massoud Alahi