| Documentation | Build Status |
|---|---|
 |
  |
This package implements the Focusing Belief Propagation algorithm for committee machines with binary weights described in the paper Unreasonable Effectiveness of Learning Neural Networks: From Accessible States and Robust Ensembles to Basic Algorithmic Schemes by Carlo Baldassi, Christian Borgs, Jennifer Chayes, Alessandro Ingrosso, Carlo Lucibello, Luca Saglietti and Riccardo Zecchina, Proc. Natl. Acad. Sci. U.S.A. 113: E7655-E7662 (2016), doi:10.1073/pnas.1608103113.
The code is written in Julia.
The package is tested against Julia 0.5, 0.6 and current (at the time of writing) 0.7-DEV on Linux, OS X, and Windows.
To install the module, use this command from within Julia:
julia> Pkg.clone("https://github.com/carlobaldassi/BinaryCommitteeMachineFBP.jl")
Dependencies will be installed automatically.
- LATEST — in-development version of the documentation.