computational-graphs

Tutorial code on how to build your own Deep Learning System in 2k Lines

Lightweight and Scalable framework that combines mainstream algorithms of Click-Through-Rate prediction based computational DAG, philosophy of Parameter Server and Ring-AllReduce collective communication.

Interactive Notation for Computational Graphs

A collection of all projects pertaining to different layers in the SDC software stack

AutoDiff DAG constructor, built on numpy and Cython. A Neural Turing Machine and DeepQ agent run on it. Clean code for educational purpose.

Strongly-typed, dependency based application framework for code/data separation with dependency injection and data passing.

C++ implementation of neural networks library with Keras-like API. Contains majority of commonly used layers, losses and optimizers. Supports sequential and multi-input-output (flow) models. Supports single CPU, Multi-CPU and GPU tensor operations (using cuDNN and cuBLAS).

Code for "Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?" [ICML 2023]

Model-based Policy Gradients

A computational graph for time-series processing.

ICDSS Machine Learning Workshop Series: Neural Networks

See how backpropagation and chain rule work in neural networks

Computational graph-based discrete choice models

Auto-differentiation library for javascript

C++ API to create Neural Nets using Eigen library

Computation Graph framework implemented using only NumPy

Automatic differentiation in python

Parameter Estimation of LOGIT-based Stochastic User Equilibrium models using computational graphs and day-to-day system-level data

A simple Java AI library for personal use.

A general purpose framework for building and running computational graphs.