3 citations · 5 across the 8 of their papers we have counts for
Showing 2023Show all
3 papers · 1 filter
cs.LG2023
Automatic Optimisation of Normalised Neural Networks
Namhoon Cho, Hyo-Sang Shin
We propose automatic optimisation methods considering the geometry of matrix manifold for the normalised parameters of neural networks. Layerwise weight normalisation with respect…
cs.LG2023
Robust Recurrent Reinforcement Learning under Evolving Hidden Disturbances with Application to Rover Wheel Slip
Saki Omi, Hyo-Sang Shin, Namhoon Cho +2
Reinforcement learning (RL) performs well in continuous-control tasks, but evolving hidden disturbances create partial observability: the agent must infer decision-relevant latent…
math.OC2023
A Passivity-Based Method for Accelerated Convex Optimisation
Namhoon Cho, Hyo-Sang Shin
This study presents a constructive methodology for designing accelerated convex optimisation algorithms in continuous-time domain. The two key enablers are the classical concept of…