Dynamic neural network library
DyNet (formerly known as cnn) is a neural network library that is written in C++ with bindings in Python. It is designed to be efficient when run on either CPU or GPU, and works well with networks that have dynamic structures that change for every training instance. Read the documentation to get started, and feel free to contact the dynet-users group group or github page with any questions, issues, or contributions.
- Latest Code: Can be found on the github page master branch.
- Latest Release: v1.0-rc1