DeepFHT parameterizes first-hitting-time diffusion processes with neural networks to produce closed-form, interpretable survival and hazard functions that match Cox-level accuracy on tested data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Neural Diffusion Processes for Physically Interpretable Survival Prediction
DeepFHT parameterizes first-hitting-time diffusion processes with neural networks to produce closed-form, interpretable survival and hazard functions that match Cox-level accuracy on tested data.