What is interpretability?

A Erasmus, TDP Brunet, E Fisher - Philosophy & Technology, 2021 - Springer
We argue that artificial networks are explainable and offer a novel theory of interpretability.
Two sets of conceptual questions are prominent in theoretical engagements with artificial …

Ynot: dependent types for imperative programs

A Nanevski, G Morrisett, A Shinnar… - Proceedings of the 13th …, 2008 - dl.acm.org
We describe an axiomatic extension to the Coq proof assistant, that supports writing,
reasoning about, and extracting higher-order, dependently-typed programs with side-effects …

Proof assistants: History, ideas and future

H Geuvers - Sadhana, 2009 - Springer
In this paper I will discuss the fundamental ideas behind proof assistants: What are they and
what is a proof anyway? I give a short history of the main ideas, emphasizing the way they …

History of interactive theorem proving

J Harrison, J Urban, F Wiedijk - Handbook of the History of Logic, 2014 - Elsevier
By interactive theorem proving, we mean some arrangement where the machine and a
human user work together interactively to produce a formal proof. There is a wide spectrum …

[图书][B] Dense sphere packings: a blueprint for formal proofs

TC Hales - 2012 - books.google.com
The 400-year-old Kepler conjecture asserts that no packing of congruent balls in three
dimensions can have a density exceeding the familiar pyramid-shaped cannonball …

A fully automatic theorem prover with human-style output

M Ganesalingam, WT Gowers - Journal of Automated Reasoning, 2017 - Springer
A Fully Automatic Theorem Prover with Human-Style Output | Journal of Automated Reasoning
Skip to main content SpringerLink Log in Menu Find a journal Publish with us Search Cart …

Formally verified software in the real world

G Klein, J Andronick, M Fernandez, I Kuz… - Communications of the …, 2018 - dl.acm.org
Formally verified software in the real world Page 1 68 COMMUNICATIONS OF THE ACM |
OCTOBER 2018 | VOL. 61 | NO. 10 contributed articles IN FEBRUARY 2017, a helicopter took …

PROSA: A case for readable mechanized schedulability analysis

F Cerqueira, F Stutz… - 2016 28th Euromicro …, 2016 - ieeexplore.ieee.org
Motivated by a string of recent errata, the paper argues that mechanized, yet readable
schedulability proofs are desirable, feasible to create with current tools and with reasonable …

Higher-Order Confluence and Universe Embedding in the Logical Framework

G Ferey - 2021 - theses.hal.science
In the context of the multiplicity of formal systems, it has become a growing need to express
formal proofs into a common logical framework. This thesis focuses on the use of higher …

Intersymbolic AI: Interlinking symbolic AI and subsymbolic AI

A Platzer - International Symposium on Leveraging Applications of …, 2024 - Springer
This perspective piece calls for the study of the new field of Intersymbolic AI, by which we
mean the combination of symbolic AI, whose building blocks have inherent …