Mathematics & AI

Mathematics & AI

Mathematics & AI is an open-access, peer-reviewed journal at the intersection of mathematics and artificial intelligence. The journal publishes original research in mathematical foundations of AI, machine learning theory, optimization, statistical learning, neural network analysis, computational mat...

Recent Articles

Detecting Hallucinations In LLM Responses Using Token-level Log-probability Signals

Large language models (LLMs) have proven themselves to be powerful tools for many natural language tasks — from being a high-quality text classifiers to acting as agents in complex retrieval-augmented...

Operator Learning for High-Dimensional Symplastic Growth Dynamics with Stochastic Cell Division

We study operator learning for a nonlinear dynamical system describing symplastic plant leaf growth with multiple interacting cell files and stochastic cell division. The biomechanical model consists...

Estimating Importance of Highly Correlated Features Using Matrix Factorization

Hyperspectral images contain a large volume of source data that exhibits high correlations along neighboring spectral bands. This makes it necessary to select the most informative features among corre...

Mathematics of natural Intelligence

In the process of evolution, the brain has achieved such perfection that artificial intelligence systems do not have and which needs its own mathematics. The concept of cognitome, introduced by the...

AI-Based Detection of Unwanted Behavior: The Paradoxical Effect of Standard Data Augmentation in Video Surveillance

Public spaces and commercial environments face persistent challenges regarding human misconduct. Traditional surveillance remains passive, while manual monitoring is labor-intensive and inefficient. C...

Explainable AI for Mathematics: Proofs as Code with Knowledge Graph and Domain Ontology Support

We investigate whether structured knowledge retrieval from a mathematical library's dependency graph can improve neural theorem proving at inference time while maintaining explainability of the retrie...

OLORA+: A HYBRID APPROACH TO PARAMETER- EFFICIENT FINE-TUNING OF LARGE LANGUAGE MODELS

Parameter-Efficient Fine-Tuning (PEFT) is essential for adapting Large Language Models (LLMs) under resource constraints, yet existing methods often treat initialization and optimization as separate c...

Application of blurry models for semantic modelling of object domains

Semantic modelling plays an important role in data processing, enabling a deep understanding of information and the development of intelligent systems. One of the methods is a four-level model of know...

The Evolution of Mind: Emergence of Collective Intelligence through Logical-Probabilistic Knowledge Dynamics in Multi-Agent ENIGMA Metaverse Ecosystems

Modern metaverse platforms, populated by heterogeneous multi-agent systems (MAS), generate vast streams of experiential data whose epistemic value remains largely untapped. This paper introduces the E...

Random forest regression and Shapley additive explanation for effective dose rate estimation in high-energy neutron fields based on Bonner spectrometer measurements

The article proposes a method for assessing the neutron energy spectrum and effective dose rate of personnel based on the readings of a Bonner spectrometer (BSS) for high-energy neutron fields. Neutro...