Past year
All results
- All results
- Verbatim
7 days ago · This paper studies complexity measures of reservoir systems. For this purpose, a more general model that we call a feature-based learning system, ...
Missing: Proving. | Show results with:Proving.
Apr 28, 2024 · This paper presents a pioneering comprehensive survey of deep learning for theorem proving by offering i) a thorough review of existing approaches across ...
Apr 25, 2024 · A curated collection of resources related to deep learning for theorem proving. We categorize papers primarily based on the applications of deep learning ...
Oct 8, 2024 · We present LeanAgent, a novel lifelong learning framework for theorem proving that continuously generalizes to and improves on ever-expanding mathematical ...
Sep 3, 2024 · SubgoalXL represents a significant step forward in the field of AI-powered theorem proving. By combining novel methodologies with state-of-the-art hardware.
Nov 22, 2023 · The term “subgoal-based proof” is used to describe the in-context examples that are generated during the subgoal refinement process, as detailed in Section 2.1.
Jan 20, 2024 · The general idea in these approaches is that machine learning limits the number of premises that are then used in a rule-based automated theorem proving ...
Aug 18, 2024 · Based on whether the proof is correct, the model receives a binary reward (1 for correct, 0 for incorrect), which it uses to refine future proof attempts.
Dec 15, 2023 · Automated theorem proving is a subfield of automated reasoning and mathematical logic dealing with proving mathematical theorems by computer programs.
Missing: Feature- | Show results with:Feature-
Oct 11, 2024 · The first life-long learning agent for formal theorem proving in lean, proving 162 theorems previously unproved by humans across 23 diverse lean mathematics ...