Difference between revisions of "Differentiable Programming"
| Line 16: | Line 16: | ||
<img src="http://pathmind.com/images/wiki/differentiable_probabilistic.jpg" width="800" height="500"> | <img src="http://pathmind.com/images/wiki/differentiable_probabilistic.jpg" width="800" height="500"> | ||
| + | |||
| + | <youtube>qhPBfysSYI8</youtube> | ||
| + | <youtube>lk0PhtSHE38</youtube> | ||
| + | <youtube>5NeqdfUPUm4</youtube> | ||
| + | <youtube>Sv3d0k7wWHk</youtube> | ||
Revision as of 17:24, 26 April 2020
YouTube search... ...Google search
Differentiable programs are programs that rewrite themselves at least one component by optimizing along a gradient, like neural networks do using optimization algorithms such as gradient descent. Here’s a graphic illustrating the difference between differential and probabilistic programming approaches. A Beginner's Guide to Differentiable Programming | Chris Nicholson - A.I. Wiki pathmind
TensorFlow 1 uses the static graph approach, whereas TensorFlow 2 uses the dynamic graph approach by default. Differentiable programming | Wikipedia
