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.
All labels observed (2)
| Label | Occurrences |
|---|---|
| Theano canonical | 10 |
| Theano numerical computation library | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T849724 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Theano Context triple: [Keras, supportsBackend, Theano]
-
A.
TensorFlow
TensorFlow is an open-source, end-to-end machine learning and deep learning framework widely used for building, training, and deploying neural network models at scale.
-
B.
Keras
Keras is a high-level neural networks API written in Python that simplifies building, training, and deploying deep learning models, often running on top of frameworks like TensorFlow.
-
C.
PyTorch
PyTorch is an open-source deep learning framework widely used for building and training neural networks, known for its dynamic computation graph and strong support for research and production in Python.
-
D.
CuPy
CuPy is an open-source array library for Python that accelerates numerical computing by providing a NumPy-compatible interface backed by GPU execution.
-
E.
Swift for TensorFlow
Swift for TensorFlow is an experimental machine learning platform that integrates TensorFlow directly into the Swift programming language to enable differentiable programming and high-performance model development.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Theano Target entity description: 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.
-
A.
TensorFlow
TensorFlow is an open-source, end-to-end machine learning and deep learning framework widely used for building, training, and deploying neural network models at scale.
-
B.
Keras
Keras is a high-level neural networks API written in Python that simplifies building, training, and deploying deep learning models, often running on top of frameworks like TensorFlow.
-
C.
PyTorch
PyTorch is an open-source deep learning framework widely used for building and training neural networks, known for its dynamic computation graph and strong support for research and production in Python.
-
D.
CuPy
CuPy is an open-source array library for Python that accelerates numerical computing by providing a NumPy-compatible interface backed by GPU execution.
-
E.
Swift for TensorFlow
Swift for TensorFlow is an experimental machine learning platform that integrates TensorFlow directly into the Swift programming language to enable differentiable programming and high-performance model development.
- F. None of above. chosen
Statements (54)
| Predicate | Object |
|---|---|
| instanceOf |
Python library
ⓘ
numerical computation library ⓘ open-source software ⓘ |
| developer |
LISA lab
ⓘ
MILA ⓘ
linked to:
Mila
Université de Montréal ⓘ |
| 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
ⓘ
CUDA ⓘ
linked to:
NVIDIA CUDA
Python ⓘ |
| influenced |
JAX
ⓘ
MXNet ⓘ PyTorch ⓘ TensorFlow ⓘ |
| initialReleaseYear | 2008 ⓘ |
| isFreeSoftware | true ⓘ |
| lastMajorReleaseYear | 2017 ⓘ |
| latestStableVersion | 1.0 ⓘ |
| license | BSD license ⓘ |
| 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 ⓘ |
| 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 ⓘ Lasagne ⓘ PyMC3 ⓘ |
| website | http://deeplearning.net/software/theano/ ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: Theano Description of subject: 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.
Referenced by (11)
Full triples — surface form annotated when it differs from this entity's canonical label.