Uncertainty-Aware Training and Computational Scaling for Hybrid Neural Pipeline Models: Heteroscedastic Loss Functions, Mixed Precision, and Multi-GPU Optimisation. foefujs [Internet]. 2026 May 31 [cited 2026 Oct. 28];3(2):272-86. Available from: https://js.foefugusau.com.ng/index.php/foefujs/article/view/442