computational-graph

An algorithm that implements intelligence based on a Method pool (a collection containing multiple types of functions). 一种基于方法池（包含多种类型的函数的集合）实现智能的算法

RusTorch is a production-grade deep learning framework re-imagined in Rust. It combines the usability you love from PyTorch with the performance, safety, and concurrency guarantees of Rust. Say goodbye to GIL locks, GC pauses, and runtime errors. Say hello to RusTorch.

Flow Based Programming in Go

A rust implementation of Andrej Karpathy's Micrograd

Realization of computational graph as multilist in C with neural network implementation.

Lightweight performat Python 3.12+ automatic differentiation system that leverages PyTorch’s computational graph to compute arbitrary-order partial derivatives.

Bài Tập Thực Hành Xây Dựng Chương Trình Dự Đoán Điểm Cuối Kỳ Sử Dụng Model Simple Linear Regression (Hồi Quy Tuyến Tính Đơn Biến) Kết Hợp Với Computational Graph (Đồ Thị Tính Toán) - Môn Cấu Trúc Dữ Liệu Và Giải Thuật Nâng Cao (CS523) - Trường Đại Học Công Nghệ Thông Tin - ĐHQG.TPHCM (UIT).

This code uses computational graph and neural network to solve the five-layer traffic demand estimation in Sioux Falls network. It also includes comparison of models and 10 cross-validations.

vanilla, simple, node-oriented, compositive, optimized, frameworkn't{torchn't, TFn't, candlen't}

A Pure Python Deep Learning Framework with Automatic Differentiation and PyTorch-like API

Reverse-mode automatic differentiation from scratch — a scalar autograd engine and neural network library in 141 lines of dependency-free Python. Gradients verified against PyTorch.

Manual implementation of backpropagation on a custom computational graph with gradient checking. Benchmarks Vanilla SGD, Momentum, and Adam optimizers from first principles using NumPy.

Computational Graph Library for Neural Network Training

A minimal vectorized automatic differentiation engine for learning how backpropagation, broadcasting, and neural networks work under the hood.

Understanding of Deep Learning Training Framework

Deep learning Library and mini-Framework built from Scratch,implementing an simplified version of PyTorch using only NumPy

The implementation of automatic differentiation based on NumPy

🎢 IaaS visual editor to create & deploy data processing pipelines - python, rmq, react, meteorjs

A lightweight, reverse-mode Automatic Differentiation (AD) engine built from scratch using Python and NumPy. Supports dynamic computational graphs and complex linear algebra operations.

A lightweight, zero-dependency reverse-mode automatic differentiation engine that implements the chain rule over computational graphs from scratch.