Special Issue on “Mathematics and Artificial Intelligence: Exploring Synergies”

Special Issue on “Mathematics and Artificial Intelligence: Exploring Synergies”


Introduction: The field of artificial intelligence (AI) has witnessed remarkable advancements in recent years, permeating various aspects of our lives. Concurrently, the significance of mathematics in AI has become increasingly evident, as sophisticated mathematical techniques are indispensable for developing and optimizing AI models. This special issue aims to delve into the profound synergy between mathematics and AI, highlighting the latest breakthroughs and discoveries in this dynamic field.

Objective: This special issue endeavors to provide a prominent platform for researchers to showcase their most recent results and insights regarding the interplay between mathematics and AI. By bringing together leading experts from both disciplines, we aim to foster novel collaborations and ignite innovative ideas that propel the advancement of AI algorithms and systems.

Topics of Interest: Contributions to this special issue may include, but are not limited to, the following topics:

  • Mathematical foundations of AI: Exploring the fundamental mathematical principles that underpin the development of AI algorithms, including probability theory, linear algebra, calculus, optimization, graph theory, and statistical inference.

  • Deep learning and neural networks: Novel mathematical techniques for understanding and improving deep learning architectures, network optimization, interpretability, generalization, and regularization.

  • Reinforcement learning and control theory: Mathematical frameworks for reinforcement learning algorithms, optimization of control policies, and the application of control theory in AI systems.

  • Explainability and interpretability in AI: Mathematical methods for generating interpretable explanations and justifications for AI model decisions, model transparency, fairness, and ethics.

  • Graph theory and network analysis: Mathematics-based approaches for analyzing complex networks, graph neural networks, graph algorithms, and their applications in AI tasks such as social network analysis and recommendation systems.

  • Bayesian inference and probabilistic modeling: Mathematical foundations and techniques for uncertainty quantification, probabilistic graphical models, Bayesian optimization, and Bayesian deep learning.

  • Optimization algorithms for AI: Advanced optimization techniques and algorithms for training AI models, including stochastic gradient descent, evolutionary algorithms, metaheuristics, and convex optimization.

  • Mathematics for natural language processing: Mathematical models and algorithms for natural language understanding, machine translation, sentiment analysis, text summarization, and question-answering systems.

Topics of interest: We invite original research papers that explore the interplay between mathematics and AI. Topics of interest include, but are not limited to:

  • Mathematical foundations of AI algorithms

  • Optimization and control theory for AI systems

  • Statistical learning and inference in AI

  • Topological data analysis and machine learning

  • Algebraic structures and deep learning

  • Game theory and AI

  • Geometric deep learning

  • Quantum computing and AI

Important dates:

  • Paper submission deadline: December 31, 2023

  • Notification of acceptance: March 31, 2024

  • Final papers due: June 31, 2024

  • Expected publication date: Mid-2024

Guest Editors

Dr. Sathishkumar Karupusamy, Senior Lecturer, Bharathiar University, Tamilnadu, India. Email: sathishkumar@gascgobi.ac.in / sathishkumark@ieee.org

Dr. Abolfazl Mehbodniya, Kuwait College of Science and Technology (KCST), Safat, Kuwait. Email: a.niya@kcst.edu.kw

Dr. Yu-Chen Hu, Distinguished Professor, Dept. of Computer Science and Information Management, Providence University, TaichungCity43301Taiwan, Republic of China (ROC). Email: ychu@pu.edu.tw / yuchen.martin.hu@gmail.com