1 citations · 2 across the 3 of their papers we have counts for
3 papers
cs.LG2024★ 1 cited
Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning
Mohamed Elsayed, A. Rupam Mahmood
Deep representation learning methods struggle with continual learning, suffering from both catastrophic forgetting of useful units and loss of plasticity, often due to rigid and un…
cs.IT2023
Terahertz Multiple Access: A Deep Reinforcement Learning Controlled Multihop IRS Topology
Muhammad Shehab, Abdullateef Almohamad, Mohamed Elsayed +5
We investigate THz communication uplink multiple access using cascaded intelligent reflecting surfaces (IRSs) assuming correlated channels. Two independent objectives to be achieve…
cs.LG2023★ 1 cited
Utility-based Perturbed Gradient Descent: An Optimizer for Continual Learning
Mohamed Elsayed, A. Rupam Mahmood
Modern representation learning methods often struggle to adapt quickly under non-stationarity because they suffer from catastrophic forgetting and decaying plasticity. Such problem…