MLNN 2026 (International Conference on Machine Learning and Neural Networks) is an academic conference held in Chengdu, China on 2026-04-10. The paper submission deadline is 2026-03-20.
The topics of interest for submission include, but are not limited to:
l Machine Learning Algorithms and Techniques
· Supervised and Unsupervised Learning: Methods and Applications
· Deep Learning Architectures and Their Applications
· Reinforcement Learning for Autonomous Systems and Robotics
· Transfer Learning and Domain Adaptation
· Evolutionary and Hybrid Algorithms for Machine Learning Optimization
· Semi-supervised Learning and Meta-learning Approaches
· Ensemble Learning and Online Learning for Dynamic Data
· Probabilistic Models: Bayesian Networks and Markov Models
· Computational Complexity and Optimization in Machine Learning
· Real-world Applications of Machine Learning in Industry and Society
l Machine Learning and Neural Networks in Communication Systems
· Machine Learning for Wireless Communication and 5G Networks
· AI-based Optimization and Resource Allocation in Communication Networks
· Deep Learning for Signal Processing, Channel Estimation, and Spectrum Managemen
· Cognitive Radio Networks and Machine Learning for Dynamic Spectrum Access
· Neural Networks for MIMO Systems, Beamforming, and Network Security
· Machine Learning for Network Traffic Prediction and Intrusion Detection
· AI Techniques for Quality of Service (QoS) and Quality of Experience (QoE) in Networks
· Data-driven Approaches for IoT and Autonomous Communication Systems
· Deep Reinforcement Learning for Communication Network Optimization
l Neural Networks and Deep Learning
· Convolutional and Recurrent Neural Networks in Computer Vision and Time Series
·Generative Models: GANs and Autoencoders in Data Generation and Dimensionality Reduction
· Neural Networks in Natural Language Processing and Speech Recognition
· Deep Reinforcement Learning for Robotics, Automation, and Network Optimization
· Neural Networks in Healthcare: Medical Imaging, Diagnostics, and Anomaly Detection
· Neural Networks for Financial Forecasting and Cybersecurity
· Transfer Learning and Few-shot Learning in Deep Learning
· Deep Learning for Recommender Systems and Data Augmentation
l Other related topics