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.

More Information

For more information visit the autograd website.

Available Versions

These versions of autograd are available on the BEAR systems (BlueBEAR, BEARCloud VMs, and CaStLeS VMs). These will be retained in accordance with our Applications Support and Retention Policy.