CompeteSMoE - Effective Training of Sparse Mixture of Experts via Competition

no code implementations • 4 Feb 2024 • Quang Pham, Giang Do, Huy Nguyen, TrungTin Nguyen, Chenghao Liu, Mina Sartipi, Binh T. Nguyen, Savitha Ramasamy, XiaoLi Li, Steven Hoi, Nhat Ho

Sparse mixture of experts (SMoE) offers an appealing solution to scale up the model complexity beyond the mean of increasing the network's depth or width.

Improving RF-DNA Fingerprinting Performance in an Indoor Multipath Environment Using Semi-Supervised Learning

no code implementations • 2 Apr 2023 • Mohamed k. Fadul, Donald R. Reising, Lakmali P. Weerasena, T. Daniel Loveless, Mina Sartipi

SEI is advantageous because it is a passive technique that exploits inherent and distinct features that are unintentionally added to the signal by the IoT Radio Frequency (RF) front-end.

Generative Adversarial Network