Replicated Stochastic Gradient Descent on Commitee machines with binary weights
Julia
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
docs
src
test
.gitignore
.travis.yml
LICENSE.md
README.md
REQUIRE
appveyor.yml

README.md

BinaryCommitteeMachineRSGD.jl

Documentation Build Status

This package implements the Replicated Stochastic Gradient Descent 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 0.4, 0.5 and current 0.6-dev on Linux, OS X, and Windows.

Installation

To install the module, use this command from within Julia:

julia> Pkg.clone("https://github.com/carlobaldassi/BinaryCommitteeMachineRSGD.jl")

Dependencies will be installed automatically.

Documentation

  • LATESTin-development version of the documentation.