This work reports direct GPU energy measurements on two workloads that batch very differently, recurrent policies in GPU-vectorised multi-agent reinforcement learning (MARL) and mixture-of-experts (MoE) language models, and asks one question of both: can the rows of a batch be made to share computation, across the batc...
This article presents the Steady-State Visual Evoked Potential (SSVEP)-Motor Imagery (MI) Electroencephalography (EEG) Dataset (SMED), a dual-paradigm EEG dataset for brain–computer interface (BCI) research that integrates both paradigms within a single experimental framework. EEG recordings were acquired from 22 parti...
Yuan-Kun Chen, Xi-Yu Shi, V. De Silva· IEEE Data Descriptions· 0 citations
A deep generative model based on conditional variational autoencoders with the objective of augmenting the vital signs of healthy individuals in a way that mimics the patterns of a certain clinical condition is proposed.
Rafael Pina, Varuna De Silva, Mindula Illeperuma· International Conference on...· 0 citations
A deep analysis of message characteristics is provided, proving that MARC maintains high operational performance even under significant data compression, offering a scalable path for deploying intelligent agents in resource-constrained environments.
Rafael Pina, Varuna De Silva, Corentin Artaud· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.