Theano

E99360

Theano is an open-source numerical computation library for Python that allows efficient definition, optimization, and evaluation of mathematical expressions, particularly those involving multi-dimensional arrays, and was widely used as a backend for deep learning frameworks.


Statements (54)
Predicate Object
instanceOf Python library
numerical computation library
open-source software
developer LISA lab
Mila
surface form: "MILA"

Université de Montréal NERFINISHED
discontinuationAnnouncementYear 2017
feature CPU optimization
GPU acceleration
automatic differentiation
automatic gradient computation
broadcasting of arrays
graph-based optimization
just-in-time compilation
shared variables
symbolic expression definition
implementationLanguage C
NVIDIA CUDA
surface form: "CUDA"

Python
influenced JAX
MXNet
PyTorch NERFINISHED
TensorFlow NERFINISHED
initialReleaseYear 2008
isFreeSoftware true
lastMajorReleaseYear 2017
latestStableVersion 1.0
license BSD license NERFINISHED
maintenanceStatus no new major features
namedAfter Theano of Croton
openSource true
operatingSystem cross-platform
optimizedFor deep learning models
large-scale numerical computation
originalAuthor Yoshua Bengio NERFINISHED
primaryDomain deep learning
machine learning
numerical computation
programmingLanguage Python
repository https://github.com/Theano/Theano
status discontinued
supportsDataStructure multi-dimensional arrays
tensors
supportsHardware CPU
GPU
supportsLanguage Python
useCase probabilistic modeling
scientific computing
training neural networks
usedAsBackendFor Blocks
Keras NERFINISHED
Lasagne
PyMC3
website http://deeplearning.net/software/theano/

Referenced by (1)

Full triples — surface form annotated when it differs from this entity's canonical label.

Keras supportsBackend Theano

Please wait…