cool paper. Uncertainty Calibration in Bayesian Neural Networks via Distance-Aware Priors

JuliaTrustworthyAI / LaplaceRedux.jl

Effortless Bayesian Deep Learning through Laplace Approximation for Flux.jl neural networks.

https://www.taija.org/LaplaceRedux.jl/

MIT License

41 stars 4 forks source link

cool paper. Uncertainty Calibration in Bayesian Neural Networks via Distance-Aware Priors #132

Open pasq-cat opened 5 days ago

pasq-cat commented 5 days ago

https://arxiv.org/pdf/2207.08200 this paper provides a different way to optimize the priors using distance aware priors. Maybe i can try to implement it.

pat-alt commented 4 days ago

Great idea!