JuliaTrustworthyAI/LaplaceRedux.jl

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

/ 100

Emerging

This tool helps machine learning practitioners evaluate how confident their deep learning models are in their predictions. You provide your pre-trained Flux.jl neural network and training data, and it outputs predictions with uncertainty estimates (like confidence intervals for regression or probability contours for classification). This is useful for anyone building and deploying deep learning models who needs to understand the reliability of those models' outputs.

Use this if you are a machine learning engineer or data scientist working with Julia and Flux.jl, and you need to quantify the uncertainty of your neural network's predictions.

Not ideal if you are not using Julia or Flux.jl for your deep learning models, or if you need highly complex or computationally intensive Bayesian deep learning methods beyond Laplace Approximation.

machine-learning-engineering deep-learning-evaluation predictive-modeling model-uncertainty julia-ecosystem

No Package No Dependents

Maintenance 10 / 25

Adoption 8 / 25

Maturity 16 / 25

Community 10 / 25

How are scores calculated?

Stars

Forks

Language

Julia

License

MIT

Higher-rated alternatives

CliMA/Oceananigans.jl

🌊 Julia software for fast, friendly, flexible, ocean-flavored fluid dynamics on CPUs and GPUs

JuliaLang/julia

The Julia Programming Language

WassimTenachi/PhySO

Physical Symbolic Optimization

FluxML/Flux.jl

Relax! Flux is the ML library that doesn't make you tensor

EnzymeAD/Enzyme.jl

Julia bindings for the Enzyme automatic differentiator

Explore ML Frameworks

All categories Trending ML Framework directory Insights