Tags : Browse Projects

CNTK (Computational Network Toolkit) by Microsoft Research, is a unified deep-learning toolkit that describes neural networks as a series of computational steps via a directed graph. In this directed graph, leaf nodes represent input values or network parameters, while other nodes represent matrix ... [More] operations upon their inputs. CNTK allows to easily realize and combine popular model types such as feed-forward DNNs, convolutional nets (CNNs), and recurrent networks (RNNs/LSTMs). It implements stochastic gradient descent (SGD, error backpropagation) learning with automatic differentiation and parallelization across multiple GPUs and servers. [Less]

Compute Library for Deep Neural Networks (clDNN) is an open source performance library for Deep Learning (DL) applications intended for acceleration of DL inference on Intel® HD Graphics Driver and Intel® Iris® graphics (also referred to as Intel® Processor Graphics). clDNN includes highly ... [More] optimized building blocks to implement convolutional neural networks (CNN) with C and C++ interfaces. We recently introduced the Intel Deep-Learning Deployment Toolkit, as part of the Intel Computer-Vision SDK to provide application developers an easy way to use the DL acceleration capabilities of Intel® Processor Graphics. [Less]