CNTK

Features Rating Results
Generic Features Rating Results
Installability
0
No votes yet
Usability
0
No votes yet
Robustness
0
No votes yet
Security
0
No votes yet
Scalability
0
No votes yet
Overall Quality
0
No votes yet
Specific Features Rating Results
Data Mining
0
No votes yet
Data Quality
0
No votes yet
Data Sources
0
No votes yet
Processing Speed
0
No votes yet
Prediction Accurancy
0
No votes yet
Description: 

CNTK (Computational Network Toolkit) by Microsoft Research, referred to The Microsoft Cognitive Toolkit, 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 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.