《计算智能研究》（Computational Intelligence Studies, CIS） 是一本国际性、同行评议的学术期刊，致力于发表计算智能理论、方法与应用领域的原创研究成果。本刊以 "仿生智能、数据驱动、自主学习" 为核心理念，聚焦神经网络、模糊系统、进化计算及其融合的新一代智能计算范式，旨在搭建人工智能、机器学习与优化计算领域的高水平交流平台，推动计算智能理论突破与在复杂系统中的创新应用。
收录范围包括但不限于：
- 神经网络与深度学习：网络架构设计、学习算法、可解释性、收敛性分析与理论基础
- 模糊系统与模糊逻辑：模糊建模、模糊控制、模糊推理、不确定性处理与粒计算
- 进化计算与群智能：遗传算法、进化策略、差分进化、粒子群、蚁群及其他元启发式算法
- 机器学习与数据驱动方法：监督 / 无监督 / 半监督学习、迁移学习、联邦学习、在线学习与增量学习
- 混合智能系统：神经 - 模糊系统、进化神经网络、模糊进化系统及多范式融合
- 智能优化与决策：多目标优化、约束优化、昂贵优化、组合优化与智能决策支持
- 概率推理与不确定性建模：贝叶斯网络、证据理论、粗糙集、置信规则库与不确定性量化
- 计算智能的可解释性、可信性与安全性：可解释 AI、对抗鲁棒性、公平性、隐私保护与伦理
- 计算智能的理论基础：学习理论、泛化能力、复杂度分析、收敛性证明与稳定性分析
- 计算智能的创新应用：模式识别、计算机视觉、自然语言处理、机器人、智能控制、生物信息学、金融工程、智慧医疗与工业优化
稿件类型： 原创研究论文（Original Research Articles）、综述论文（Review Articles/Surveys）、快报（Letters）、短讯 / 简报（Short Communications）、观点与展望（Perspectives）、应用案例（Application Notes）、社论（Editorial）及书评等。
Computational Intelligence Studies (CIS) is an international, peer-reviewed journal dedicated to publishing original research in the theory, methods, and applications of computational intelligence. Grounded in the core principles of bio-inspired intelligence, data-driven computation, and autonomous learning, the journal focuses on neural networks, fuzzy systems, evolutionary computation, and their integration as next-generation intelligent computing paradigms. It serves as a high-level platform bridging artificial intelligence, machine learning, and optimization, advancing theoretical breakthroughs in computational intelligence and their innovative applications in complex systems.
The journal welcomes submissions covering, but not limited to:
- Neural networks and deep learning: architecture design, learning algorithms, interpretability, convergence analysis, and theoretical foundations
- Fuzzy systems and fuzzy logic: fuzzy modeling, fuzzy control, fuzzy inference, uncertainty handling, and granular computing
- Evolutionary computation and swarm intelligence: genetic algorithms, evolution strategies, differential evolution, particle swarm optimization, ant colony optimization, and other metaheuristics
- Machine learning and data-driven methods: supervised/unsupervised/semi-supervised learning, transfer learning, federated learning, online learning, and incremental learning
- Hybrid intelligent systems: neuro-fuzzy systems, evolutionary neural networks, fuzzy evolutionary systems, and multi-paradigm integration
- Intelligent optimization and decision-making: multi-objective optimization, constrained optimization, expensive optimization, combinatorial optimization, and intelligent decision support
- Probabilistic reasoning and uncertainty modeling: Bayesian networks, evidence theory, rough sets, belief rule bases, and uncertainty quantification
- Interpretability, trustworthiness, and safety of computational intelligence: explainable AI, adversarial robustness, fairness, privacy preservation, and ethics
- Theoretical foundations of computational intelligence: learning theory, generalization capability, complexity analysis, convergence proofs, and stability analysis
- Innovative applications of computational intelligence: pattern recognition, computer vision, natural language processing, robotics, intelligent control, bioinformatics, financial engineering, smart healthcare, and industrial optimization
Article types include Original Research Articles, Review Articles/Surveys, Letters, Short Communications, Perspectives, Application Notes, Editorials, and Book Reviews.
