Related papers: Machine learning and information theory concepts towards an AI Mathematician

Machine learning and information theory concepts towards an AI Mathematician

URL: http://arxiv.org/abs/2403.04571v1
Date: Thu, 7 Mar 2024 15:12:06 GMT
Title: Machine learning and information theory concepts towards an AI Mathematician
Authors: Yoshua Bengio, Nikolay Malkin
Abstract summary: The current state-of-the-art in artificial intelligence is impressive, especially in terms of mastery of language, but not so much in terms of mathematical reasoning. This essay builds on the idea that current deep learning mostly succeeds at system 1 abilities. It takes an information-theoretical posture to ask questions about what constitutes an interesting mathematical statement.
Score: 77.63761356203105
License: http://creativecommons.org/licenses/by/4.0/
Abstract: The current state-of-the-art in artificial intelligence is impressive, especially in terms of mastery of language, but not so much in terms of mathematical reasoning. What could be missing? Can we learn something useful about that gap from how the brains of mathematicians go about their craft? This essay builds on the idea that current deep learning mostly succeeds at system 1 abilities -- which correspond to our intuition and habitual behaviors -- but still lacks something important regarding system 2 abilities -- which include reasoning and robust uncertainty estimation. It takes an information-theoretical posture to ask questions about what constitutes an interesting mathematical statement, which could guide future work in crafting an AI mathematician. The focus is not on proving a given theorem but on discovering new and interesting conjectures. The central hypothesis is that a desirable body of theorems better summarizes the set of all provable statements, for example by having a small description length while at the same time being close (in terms of number of derivation steps) to many provable statements.

Related papers

MathScale: Scaling Instruction Tuning for Mathematical Reasoning [70.89605383298331]
Large language models (LLMs) have demonstrated remarkable capabilities in problem-solving. However, their proficiency in solving mathematical problems remains inadequate. We propose MathScale, a simple and scalable method to create high-quality mathematical reasoning data.
arXiv Detail & Related papers (2024-03-05T11:42:59Z)
AI for Mathematics: A Cognitive Science Perspective [86.02346372284292]
Mathematics is one of the most powerful conceptual systems developed and used by the human species. Rapid progress in AI, particularly propelled by advances in large language models (LLMs), has sparked renewed, widespread interest in building such systems.
arXiv Detail & Related papers (2023-10-19T02:00:31Z)
Towards a Holistic Understanding of Mathematical Questions with Contrastive Pre-training [65.10741459705739]
We propose a novel contrastive pre-training approach for mathematical question representations, namely QuesCo. We first design two-level question augmentations, including content-level and structure-level, which generate literally diverse question pairs with similar purposes. Then, to fully exploit hierarchical information of knowledge concepts, we propose a knowledge hierarchy-aware rank strategy.
arXiv Detail & Related papers (2023-01-18T14:23:29Z)
A Survey of Deep Learning for Mathematical Reasoning [71.88150173381153]
We review the key tasks, datasets, and methods at the intersection of mathematical reasoning and deep learning over the past decade. Recent advances in large-scale neural language models have opened up new benchmarks and opportunities to use deep learning for mathematical reasoning.
arXiv Detail & Related papers (2022-12-20T18:46:16Z)
Peano: Learning Formal Mathematical Reasoning [35.086032962873226]
General mathematical reasoning is computationally undecidable, but humans routinely solve new problems. We posit that central to both puzzles is the structure of procedural abstractions underlying mathematics. We explore this idea in a case study on 5 sections of beginning algebra on the Khan Academy platform.
arXiv Detail & Related papers (2022-11-29T01:42:26Z)
The Role of General Intelligence in Mathematical Reasoning [0.0]
Objects are a centerpiece of the mathematical realm and our interaction with and reasoning about it. In contemporary cognitive science and A.I., the physical and mathematical domains are customarily explored separately. I describe an abstract theoretical framework for learning object representations, that makes room for mathematical objects on par with non-mathematical ones.
arXiv Detail & Related papers (2021-04-27T20:43:25Z)
Inductive Biases for Deep Learning of Higher-Level Cognition [108.89281493851358]
A fascinating hypothesis is that human and animal intelligence could be explained by a few principles. This work considers a larger list, focusing on those which concern mostly higher-level and sequential conscious processing. The objective of clarifying these particular principles is that they could potentially help us build AI systems benefiting from humans' abilities.
arXiv Detail & Related papers (2020-11-30T18:29:25Z)
Discrete Math with Programming: A Principled Approach [0.0]
It has long been argued that discrete math is better taught with programming. This paper introduces an approach that supports all central concepts of discrete math. Math and logical statements can be expressed precisely at a high level and be executed on a computer.
arXiv Detail & Related papers (2020-11-28T03:41:27Z)
Noisy Deductive Reasoning: How Humans Construct Math, and How Math Constructs Universes [0.5874142059884521]
We present a computational model of mathematical reasoning according to which mathematics is a fundamentally process. We show that this framework gives a compelling account of several aspects of mathematical practice.
arXiv Detail & Related papers (2020-10-28T19:43:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.