RNNLIB is a recurrent neural network library for sequence learning problems. Applicable to most types of spatiotemporal data, it has proven particularly effective for speech and handwriting recognition.
full installation and usage instructions given at
http://sourceforge.net/p/rnnl/wiki/Home/
Features
- LSTM
- Multidimensional recurrent neural networks
- Connectionist temporal classification
- Adaptive weight noise (stochastic variational inference)
License
GNU General Public License version 3.0 (GPLv3)Follow RNNLIB
You Might Also Like
Workload Automation for Global Enterprises
Redwood lets you orchestrate securely and reliably across any application, service or server, in the cloud or on-premise, all inside a single platform.
Rate This Project
Login To Rate This Project
User Reviews
-
Train LSTMs quickly on the CPU!
-
doc is incomplete, and there are a lot of problems such as can not get the predict labels and use the trained model to predict....