There are 4 repositories under computation-graph topic.
Self-contained Machine Learning and Natural Language Processing library in Go
Implementing Multiple Layer Neural Network from Scratch
(Spring 2017) Assignment 2: GPU Executor
Deep Learning framework in C++/CUDA that supports symbolic/automatic differentiation, dynamic computation graphs, tensor/matrix operations accelerated by GPU and implementations of various state-of-the-art graph neural networks and other Machine Learning models including Covariant Compositional Networks For Learning Graphs [Risi et al]
Build, distribute, and execute task graphs
Computational graph library for machine learning
Model-based Policy Gradients
A computation graph micro-framework providing seamless lazy and concurrent evaluation
GenCoG: A DSL-Based Approach to Generating Computation Graphs for TVM Testing (ISSTA‘23)
A short collection of Jupyter notebooks explaining some basic computational math
artifax is a Python package to evaluate nodes in a computation graph where the dependencies associated with each node are extracted directly from their function signatures.
C computation graph, AutoGrad with OpenCL support [WIP]
Real-time execution and remote monitoring and tuning of BDSim Block-Diagrams for modeling and control of Dynamical Systems
a single c++ file for learing how data flow graphs work.
An easy-to-use dynamic computation graph library for running e2e ML training.
Creating and analyzing interaction graphs based on boolean functions
Python library for developing data processing algorithms as computational graphs and their integration with publish-subscribe systems
Implementation of automatic differentiation (AD) in forward and backward modes with mathematical explanations
To become a comprehensive platform for users to execute data processing and AI model training tasks using Ocean nodes within the C2DV2 architecture.
Quaternion is a framework for building and executing node-based computational graphs.
A tiny library to build hierarchical computation graphs that isolate function logic while avoiding duplicate work
Assignment 1: automatic differentiation
this is TLE eliminators assignment which is contest tracker fetches realtime contest data and automation of uploading of youtube channel contest solution link to the database.
Supporting material for Academy Course DAT31050
The implementation of a deep learning framework from scratch in plain Numpy.