BrightWire.Net4 2.1.1

Bright Wire Machine Learning

Bright Wire is an open source machine learning library. Includes neural networks (feed forward, convolutional and recurrent), naive bayes, linear regression, decision trees, logistic regression, k-means clustering and dimensionality reduction.

Install-Package BrightWire.Net4 -Version 2.1.1
dotnet add package BrightWire.Net4 --version 2.1.1
<PackageReference Include="BrightWire.Net4" Version="2.1.1" />
For projects that support PackageReference, copy this XML node into the project file to reference the package.
paket add BrightWire.Net4 --version 2.1.1
The NuGet Team does not provide support for this client. Please contact its maintainers for support.

Enhancements:

  • csv parser now parses numbers with commas
  • exposed data table adaptor base classes
  • exposed vectorisation model from default data table adaptor
  • added suport for boolean columns as binary vectorisation columns
  • weighted index list to index list conversion
  • added naive bayes training from data tables
  • added column constraints to data table analysis xml
  • vector distances refactor and performance improvements
  • added confusion matrix from data table
  • added reverse normalise and reverse vectorise for output columns from normalisation model
  • matrix columns/rows as vectors
  • batch normalisation
  • added output nodes and slots so that graphs can output multiple results

Bug Fixes:

  • fixed filter initialisation when dropout percentage is 0
  • bin overflow correction

Enhancements:

  • csv parser now parses numbers with commas
  • exposed data table adaptor base classes
  • exposed vectorisation model from default data table adaptor
  • added suport for boolean columns as binary vectorisation columns
  • weighted index list to index list conversion
  • added naive bayes training from data tables
  • added column constraints to data table analysis xml
  • vector distances refactor and performance improvements
  • added confusion matrix from data table
  • added reverse normalise and reverse vectorise for output columns from normalisation model
  • matrix columns/rows as vectors
  • batch normalisation
  • added output nodes and slots so that graphs can output multiple results

Bug Fixes:

  • fixed filter initialisation when dropout percentage is 0
  • bin overflow correction

Version History

Version Downloads Last updated
2.1.1 138 2/23/2019
2.1.0 224 9/30/2018
2.0.6 197 7/27/2018
2.0.5 2,630 1/4/2018
2.0.4 417 9/23/2017
2.0.3 5,404 8/18/2017
2.0.2 474 6/21/2017
2.0.1 278 6/19/2017
2.0.0 223 6/7/2017
1.1.6 331 3/10/2017
1.1.5 217 3/3/2017
1.1.4 364 1/24/2017
1.1.3 264 1/19/2017
1.1.2 257 1/12/2017
1.1.1 301 12/8/2016
1.1.0 253 11/7/2016
1.0.8 239 10/31/2016
1.0.7 286 10/27/2016
1.0.5 254 10/25/2016
1.0.4 239 10/21/2016
1.0.3 241 10/18/2016
1.0.2 238 10/17/2016
1.0.1 244 10/14/2016
1.0.0 235 10/12/2016