RNN in Julia for MNIST digit recognition implemented with automatic differentiation. Over 96% accuracy.
-
Updated
Jun 21, 2024 - Jupyter Notebook
RNN in Julia for MNIST digit recognition implemented with automatic differentiation. Over 96% accuracy.
A general purpose framework for building and running computational graphs.
See how backpropagation and chain rule work in neural networks
Network-wide estimation of traffic flow and travel time with data-driven macroscopic models
Parameter Estimation of LOGIT-based Stochastic User Equilibrium models using computational graphs and day-to-day system-level data
Code for "Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?" [ICML 2023]
Yet another tensor automatic differentiation framework
A computational graph for time-series processing.
a compact tensor library capable of training deep neural networks on both cpu and cuda devices
A deep learning library for golang
A graph-oriented algorithmic engine
TensorFlow's very distant and not so bright cousin
Web application framework built on 1e14
Cached lazy evaluation of computational graphs
Automatic differentiation in python
Type safe computational graph interface
Regularized logistic regressions with computational graphs
A GPU-parallel Java automatic differentiation computational graph implementation.
Python library providing a collection of functions realizing common computer vision functionality, based on OpenCV and NumPy.
Add a description, image, and links to the computational-graphs topic page so that developers can more easily learn about it.
To associate your repository with the computational-graphs topic, visit your repo's landing page and select "manage topics."