3 papers
cs.LG2026
Residual-Guided Randomized Neural Networks
Mushir Akhtar, M. Tanveer, Mohd. Arshad
Randomized neural networks enable fast and analytically tractable training by fixing the input to hidden layer parameters at random and learning the output weights in closed form;…
cs.LG2026
CAWI: Copula-Aligned Weight Initialization for Randomized Neural Networks
Mushir Akhtar, M. Tanveer, Mohd. Arshad
Randomized neural networks (RdNNs) enable efficient, backpropagation-free training by freezing randomly initialized input-to-hidden weights, which permits a closed-form solution fo…
cs.LG2024
Advancing RVFL networks: Robust classification with the HawkEye loss function
Mushir Akhtar, Ritik Mishra, M. Tanveer +1
Random vector functional link (RVFL), a variant of single-layer feedforward neural network (SLFN), has garnered significant attention due to its lower computational cost and robust…