11 lines
565 B
Plaintext
11 lines
565 B
Plaintext
Autograd can automatically differentiate native Python
|
|
and Numpy code. It can handle a large subset of Python
|
|
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
|