Sketching: a Cognitively inspired Compositional Theorem Prover that Learns to Prove - a Proposal

Brando Miranda

Permalink

https://hdl.handle.net/2142/109134 Copy

Description

Title

Sketching: a Cognitively inspired Compositional Theorem Prover that Learns to Prove - a Proposal

Author(s)

Brando Miranda

Issue Date

2020-12-23

Keyword(s)

• meta-learning
• machine learning
• sketching
• theorem proving
• agi
• ai safety
• AI
• artificial general intelligence
• automatic theorem proving

Date of Ingest

2020-12-23T18:02:24Z

Abstract

Mathematics is a powerful tool that has benefited humanity for millenia. Proficiency in this subject has far reaching implications for society because physics, mechanical engineering, computer science, statistics, machine learning and the scientific method itself depend on it. For example, being able to automate mathematical proofs would allow us to create safe and interpretable A.I. because a system with provable guarantees is a system we understand and can trust. This is why in this proposal we suggest a novel way of implementing the concept of sketching for automated theorem provers using powerful ideas from cognitive science and artificial neural networks; these ideas are: compositionality, learning-to-learn, learning as model building and curriculum-learn.

Type of Resource

text

Genre of Resource

proposal

Permalink

http://hdl.handle.net/2142/109134

Owning Collections