no code implementations • 14 Mar 2024 • Atah Nuh Mih, Alireza Rahimi, Asfia Kawnine, Francis Palma, Monica Wachowicz, Rickey Dubay, Hung Cao
The results of the Caltech-101 image classification show that our model has a better test accuracy (76. 21%) than Xception (75. 89%), uses less memory on average (847. 9MB) than Xception (874. 6MB), and has faster training and inference times.
no code implementations • 4 Dec 2023 • Atah Nuh Mih, Hung Cao, Asfia Kawnine, Monica Wachowicz
The results of our experiment show that our model has a remarkable performance with a test accuracy of 73. 45% without pre-training.
no code implementations • 26 Nov 2023 • Asfia Kawnine, Hung Cao, Atah Nuh Mih, Monica Wachowicz
We posit that implementing multiple global servers in federated learning can enhance efficiency by capitalizing on local collaborations and aggregating knowledge, and the error tolerance in regard to communication failure in the single server framework would be handled.
no code implementations • 5 Oct 2023 • Atah Nuh Mih, Hung Cao, Asfia Kawnine, Monica Wachowicz
The local (edge) models are then updated with the weights of the global (server) model.
no code implementations • 26 Feb 2023 • Atah Nuh Mih, Hung Cao, Joshua Pickard, Monica Wachowicz, Rickey Dubay
Our proposed approach can be applied in defect detection applications where insufficient data is available for training a model and can be extended to identify imperfections in new unseen data.