AIMC Topic: Mathematics

Clear Filters Showing 1 to 10 of 54 articles

Personalized deep neural networks reveal mechanisms of math learning disabilities in children.

Science advances
Learning disabilities affect a substantial proportion of children worldwide, with far-reaching consequences for their academic, professional, and personal lives. Here we develop digital twins-biologically plausible personalized deep neural networks (...

Awareness, acceptance, and adoption of Gen-AI by K-12 mathematics teachers: an empirical study integrating TAM and TPB.

BMC psychology
In the 21st century, the variety of instructional media for mathematics has significantly diversified. Generative AI (Gen-AI) is one technology that K-12 teachers can utilize for teaching mathematics. However, as a new instructional medium, Gen-AI pr...

Fuzzy Set Theory Applied on Autometrized Algebra.

F1000Research
This paper introduces fuzzy subalgebras of autometrized algebras and studies their properties. Also, we present fuzzy ideals of autometrized algebras and provide examples to illustrate our findings. We examine the homomorphisms of both the images and...

Q-fuzzy structure on JU-algebra.

F1000Research
BACKGROUND: JU-algebras, an important class in abstract algebra, are extended here by incorporating fuzzy set theory to handle uncertainty in algebraic structures. In this study, we apply the concept of Q-fuzzy sets to JU-subalgebras and JU-ideals in...

A machine-learning model of academic resilience in the times of the COVID-19 pandemic: Evidence drawn from 79 countries/economies in the PISA 2022 mathematics study.

The British journal of educational psychology
BACKGROUND: Given that students from socio-economically disadvantaged family backgrounds are more likely to suffer from low academic performance, there is an interest in identifying features of academic resilience, which may mitigate the relationship...

Advanced technologies and mathematical metacognition: The present and future orientation.

Bio Systems
The intersection of mathematical cognition, metacognition, and advanced technologies presents a frontier with profound implications for human learning and artificial intelligence. This paper traces the historical roots of these concepts from the Pyth...

Solving olympiad geometry without human demonstrations.

Nature
Proving mathematical theorems at the olympiad level represents a notable milestone in human-level automated reasoning, owing to their reputed difficulty among the world's best talents in pre-university mathematics. Current machine-learning approaches...

Geometric Deep Learning sub-network extraction for Maximum Clique Enumeration.

PloS one
The paper presents an algorithm to approach the problem of Maximum Clique Enumeration, a well known NP-hard problem that have several real world applications. The proposed solution, called LGP-MCE, exploits Geometric Deep Learning, a Machine Learning...

Incorrect Application of Yilmaz-Poli (2022) Initialisation Method in dePater-Mitici 2023 paper entitled "A mathematical framework for improved weight initialization of neural networks using Lagrange multipliers".

Neural networks : the official journal of the International Neural Network Society
In this letter to the editor we report on a methodological error made in the article entitled "A mathematical framework for improved weight initialization of neural networks using Lagrange multipliers" by dePater and Mitici recently appeared in this ...

Unveiling the benefits of multitasking in disentangled representation formation.

Trends in cognitive sciences
Johnston and Fusi recently investigated the emergence of disentangled representations when a neural network was trained to perform multiple simultaneous tasks. Such experiments explore the benefits of flexible representations and add to a growing fie...