deeptrainer

DeepTrainer* is an open source project to implement heavily optimised deep learning methods for artificial neural networks. Available from: https://github.com/bulyaki/DeepTrainer 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. Currently the library is accessible through three interfaces: - A WinForms application with data visualization - A WPF application with data visualization - A self-hosted web-api (OWIN) service for cloud deployment *DeepTrainer is a trading name of Next Tier Limited, registered in England and Wales, reg. 07354214