Call for Papers

This track covers breakthrough research in supervised, unsupervised, and self-supervised learning methodologies.

Topics include deep neural network architectures, transfer learning, meta-learning, and optimization techniques for large-scale models.

We welcome papers on federated learning, privacy-preserving ML, and resource-efficient training methods.

Practical contributions demonstrating real-world deployment of ML systems are equally welcome alongside theoretical advances.

Accepted papers will be published in the IEEE Xplore Digital Library(Approval Pending) following blind peer review by a minimum of 3 reviewers.