Autograd can automatically differentiate native Python and Numpy code. It can handle a large subset of Python's features, including loops, ifs, recursion and closures, and it can even take derivatives of derivatives of derivatives. It supports reverse-mode differentiation (a.k.a. backpropagation), which means it can efficiently take gradients of scalar-valued functions with respect to array-valued arguments, as well as forward-mode differentiation, and the two can be composed arbitrarily. The main intended application of Autograd is gradient-based optimization. For more information, check out the tutorial and the examples directory. We can continue to differentiate as many times as we like, and use numpy's vectorization of scalar-valued functions across many different input values.

Features

  • Simple neural net
  • Convolutional neural net
  • Recurrent neural net
  • LSTM
  • Neural Turing Machine
  • Backpropagating through a fluid simulation

Project Samples

Project Activity

See All Activity >

License

MIT License

Follow Autograd

Autograd Web Site

Other Useful Business Software
Get Avast Free Antivirus with 24/7 AI-powered online scam detection Icon
Get Avast Free Antivirus with 24/7 AI-powered online scam detection

Get protection for today’s online threats. Free.

Award-winning antivirus protection, as well as protection against online scams, dangerous Wi-Fi connections, hacked accounts, and ransomware. It includes Avast Assistant, your built-in AI partner, which gives you help with suspicious online messages, offers, and more.
Free Download
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of Autograd!

Additional Project Details

Programming Language

Python

Related Categories

Python Source Code Analysis Tool

Registered

2021-10-12