Purpose
This workshop is organized in conjunction with the 17th International Conference on Ambient Systems, Networks and Technologies (ANT 2026) and the 9th International Conference on Emerging Data & Industry 4.0 (EDI40 2026).
Dates: April 14–16, 2026
Location: Istanbul, Türkiye
Description
The DL-SMCS 2026 workshop aims to bridge the gap between deep learning and stochastic modeling, creating a dynamic research forum that explores how advanced neural architectures can improve the modeling of complex systems characterized by uncertainty, randomness, and nonlinear dynamics.
As modern systems from biological processes to economic markets and physical environments become increasingly complex, traditional stochastic models face limitations in scalability and representation power. Deep learning, with its ability to extract patterns from high-dimensional and noisy data, offers a transformative avenue for enhancing stochastic modeling.
This workshop invites contributions that combine probabilistic methods, differential equations, diffusion processes, and deep learning architectures to model, simulate, and predict the behavior of uncertain systems. It will foster discussions between mathematicians, AI researchers, and engineers to design new hybrid frameworks that merge rigorous theory with data-driven learning.
Links