Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Structured Basis Function Networks: Loss-Centric Multi-Hypothesis Ensembles with Controllable Diversity
Alejandro Rodriguez Dominguez, Muhammad Shahzad, Xia Hong
Existing approaches to predictive uncertainty rely either on multi-hypothesis prediction, which promotes diversity but lacks principled aggregation, or on ensemble learning, which…
cs.LG2023
Structured Radial Basis Function Network: Modelling Diversity for Multiple Hypotheses Prediction
Alejandro Rodriguez Dominguez, Muhammad Shahzad, Xia Hong
Multi-modal problems can be effectively addressed using multiple hypothesis frameworks, but integrating these frameworks into learning models poses significant challenges. This pap…