Skip to content
A machine-learning library that uses the backpropagation and the resilient propagation algorithms implemented with matrix-calculations. C++ library with CLI/C++ .NET wrapper.
C# C++ Cuda Other
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
DeepTrainer
DeepTrainerCUDA
DeepTrainerLib
DeepTrainerLibCUDA
DeepTrainerLibTest
DeepTrainerTester
Releases
Wrapper
.gitattributes
DeepTrainer.sln
DeepTrainerLogo.ico
LICENSE
README.md
docker-compose.dcproj
docker-compose.override.yml
docker-compose.yml
sqr_sqrt_15000_rows.csv
sqr_sqrt_1500_rows.csv

README.md

DeepTrainerLib

Highly optimised open source machine learning library research & development

DeepTrainer is an open source project to implement heavily optimised deep learning methods for artificial neural networks.

DeepTrainer currently implements the following algorithms:

  • Backpropagation
  • Batch Backpropagation
  • Distributed Batch Backpropagation
  • Resilient Propagation
  • Distributed Resilient Propagation

With the following activation functions selectable for each layer:

  • Sigmoid
  • Hyperbolic tangent
  • Arcus tangent
  • ReLU
  • PReLU (lazy ReLU)
  • ELU
  • SoftPlus

All algorithms are making use of a matrix implementation that uses automatic partitioning (4x4 or 8x8, single or double precision), and hardware accelerated matrix operations (dot product using SSE2, AVX, AVX512).

The algorithms are implemented using C++17 in Visual Studio on Windows OS, although a portable version is planned too. More details here: https://bulyaki.com/2018/04/02/c11-dll-library-for-the-matrix-rprop-algorithm/ https://bulyaki.com/2018/04/01/old-demo-for-the-rprop-algorithm-using-matrices/ https://bulyaki.com/2013/04/14/the-matrix-form-of-the-rprop-algorithm/ https://bulyaki.com/2013/04/14/the-matrix-form-of-the-backpropagation-algorithm/

Build notes: For CPU-only build select the "Intel x86" configuration. For Nvidia CUDA acceleration select the CUDA x64 configuration.

License information for third-party packages used in this solution:

Id LicenseUrl


DevZest.WpfDocking https://opensource.org/licenses/mit-license.php
Extended.Wpf.Toolkit https://github.com/xceedsoftware/wpftoolkit/blob/master/license.md OxyPlot.Core https://raw.githubusercontent.com/oxyplot/oxyplot/master/LICENSE
OxyPlot.Wpf https://raw.githubusercontent.com/oxyplot/oxyplot/master/LICENSE
DockPanelSuite http://www.opensource.org/licenses/mit-license.php
OxyPlot.Core https://raw.githubusercontent.com/oxyplot/oxyplot/master/LICENSE
OxyPlot.WindowsForms https://raw.githubusercontent.com/oxyplot/oxyplot/master/LICENSE

You can’t perform that action at this time.