no code implementations • 28 Dec 2022 • Sakib Abrar, Ali Sekmen, Manar D. Samad
Eight clustering and state-of-the-art embedding clustering methods proposed for image data sets are tested on seven tabular data sets.
no code implementations • 17 May 2022 • Manar Samad, Sakib Abrar
Unlike dropout learning, the proposed weight perturbation routine additionally achieves 15% to 40% sparsity across six tabular data sets for the compression of deep pretrained models.
no code implementations • 28 Feb 2022 • Manar D Samad, Sakib Abrar, Norou Diawara
Our extensive analyses involving six tabular data sets, up to 80% missingness, and three missingness types (missing completely at random, missing at random, missing not at random) reveal that ensemble or deep learning within MICE is superior to the baseline MICE (b-MICE), both of which are consistently outperformed by CISCL.