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.

ICDSS Machine Learning Workshop Series: Neural Networks

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).

Model-based Policy Gradients

Automatic differentiation in python

A simple Java AI library for personal use.

Computation Graph framework implemented using only NumPy

Tools for building function graphs

Web application framework built on 1e14

A framework for developing async applications.

A graph-oriented algorithmic engine

Regularized logistic regressions with computational graphs

Python library providing a collection of common computer vision functions (based on OpenCV and NumPy) and computational graphs built from these functions (executable using EPypes)

Computational graph for Java.

Implementing a neural network classifier for cifar-10

A simple library for building computational graphs with autodiff support.

Small automatic differentiation package for scalars.

A GPU-parallel Java automatic differentiation computational graph implementation from scratch.

Code for the part 2 of the tutorial on pychain

Predict the number of bikeshare users on a given day by building my own deep-learning library.

An aggregation of my experiments in Neural Networks and Deep Learning using TensorFlow.

Code for the part 1 of the tutorial on pychain

A simple mimicking of TensorFlow, which including forward and backward propogation.

Small tools for Tensorflow.