Probabilistic Results on the Architecture of Mathematical Reasoning
Aligned by Cognitive Alternation
- URL: http://arxiv.org/abs/2308.08714v1
- Date: Thu, 17 Aug 2023 00:35:11 GMT
- Title: Probabilistic Results on the Architecture of Mathematical Reasoning
Aligned by Cognitive Alternation
- Authors: Minzheng Li, Xiangzhong Fang, Haixin Yang
- Abstract summary: We envision a machine capable of solving mathematical problems.
Dividing the quantitative reasoning system into two parts: thought processes and cognitive processes, we provide probabilistic descriptions of the architecture.
- Score: 2.034092665105039
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We envision a machine capable of solving mathematical problems. Dividing the
quantitative reasoning system into two parts: thought processes and cognitive
processes, we provide probabilistic descriptions of the architecture.
Related papers
- Towards Understanding How Transformer Perform Multi-step Reasoning with Matching Operation [52.77133661679439]
Investigating internal reasoning mechanisms of large language models can help us design better model architectures and training strategies.
We investigate the matching mechanism employed by Transformer for multi-step reasoning on a constructed dataset.
We propose a conjecture on the upper bound of the model's reasoning ability based on this phenomenon.
arXiv Detail & Related papers (2024-05-24T07:41:26Z) - Learning to Solve Geometry Problems via Simulating Human Dual-Reasoning Process [84.49427910920008]
Geometry Problem Solving (GPS) has attracted much attention in recent years.
It requires a solver to comprehensively understand both text and diagram, master essential geometry knowledge, and appropriately apply it in reasoning.
Existing works follow a paradigm of neural machine translation and only focus on enhancing the capability of encoders, which neglects the essential characteristics of human geometry reasoning.
arXiv Detail & Related papers (2024-05-10T03:53:49Z) - Exploring a Cognitive Architecture for Learning Arithmetic Equations [0.0]
This paper explores the cognitive mechanisms powering arithmetic learning.
I implement a number vectorization embedding network and an associative memory model to investigate how an intelligent system can learn and recall arithmetic equations.
I aim to contribute to ongoing research into the neural correlates of mathematical cognition in intelligent systems.
arXiv Detail & Related papers (2024-05-05T18:42:00Z) - From Probabilistic Programming to Complexity-based Programming [0.5874142059884521]
The paper presents the main characteristics and a preliminary implementation of a novel computational framework named CompLog.
Inspired by probabilistic programming systems like ProbLog, CompLog builds upon the inferential mechanisms proposed by Simplicity Theory.
The proposed system enables users to compute ex-post and ex-ante measures of unexpectedness of a certain situation.
arXiv Detail & Related papers (2023-07-28T10:11:01Z) - 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) - Kernel Based Cognitive Architecture for Autonomous Agents [91.3755431537592]
This paper considers an evolutionary approach to creating a cognitive functionality.
We consider a cognitive architecture which ensures the evolution of the agent on the basis of Symbol Emergence Problem solution.
arXiv Detail & Related papers (2022-07-02T12:41:32Z) - From Statistical to Causal Learning [9.327920030279586]
We describe basic ideas underlying research to build and understand artificially intelligent systems.
Some of the hard open problems of machine learning and AI are intrinsically related to causality.
arXiv Detail & Related papers (2022-04-01T17:55:22Z) - From the String Landscape to the Mathematical Landscape: a
Machine-Learning Outlook [0.0]
We review the recent programme of using machine-learning to explore the landscape of mathematical problems.
We highlight some experiments on how AI helps with conjecture formulation, pattern recognition and computation.
arXiv Detail & Related papers (2022-02-12T15:18:59Z) - A Two-Systems Perspective for Computational Thinking [2.4149105714758545]
This paper suggests adopting Kahneman's two-systems model as a framework to understand the computational thought process.
The potential benefits of adopting Kahneman's two-systems perspective are that it helps us to fix the biases that cause errors in our reasoning.
arXiv Detail & Related papers (2020-12-06T07:33:45Z) - Neuro-symbolic Architectures for Context Understanding [59.899606495602406]
We propose the use of hybrid AI methodology as a framework for combining the strengths of data-driven and knowledge-driven approaches.
Specifically, we inherit the concept of neuro-symbolism as a way of using knowledge-bases to guide the learning progress of deep neural networks.
arXiv Detail & Related papers (2020-03-09T15:04:07Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.