JonathanRaiman/theano_lstm
:microscope: Nano size Theano LSTM module
This is a specialized module for machine learning engineers who need to implement recurrent neural networks, particularly LSTMs, using the Theano framework. It provides core building blocks like recurrent layers, embedding layers, and various gradient optimizers. The module takes sequence data as input and produces predictions or models that capture temporal dependencies.
303 stars. No commits in the last 6 months. Available on PyPI.
Use this if you are a machine learning engineer working with Theano and need to build custom recurrent neural networks for sequence prediction tasks.
Not ideal if you are looking for a high-level, ready-to-use deep learning library or are not familiar with Theano's symbolic computation.
Stars
303
Forks
111
Language
Python
License
—
Category
Last pushed
Nov 16, 2016
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JonathanRaiman/theano_lstm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
google/tangent
Source-to-Source Debuggable Derivatives in Pure Python
ahrefs/ocannl
OCANNL: OCaml Compiles Algorithms for Neural Networks Learning
yoshoku/numo-openblas
Numo::OpenBLAS builds and uses OpenBLAS as a background library for Numo::Linalg
statusfailed/catgrad
a categorical deep learning compiler
pranftw/neograd
A deep learning framework created from scratch with Python and NumPy