Automatic Differentiation with Theano
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact mv310.
Implementing models in machine learning and data analysis often requires a considerable effort which can span over weeks. Symbolic differentiation can be used to speed up model prototyping in a large class of models to a single day. In this tutorial we will explain how to use Theano, a Python package for symbolic differentiation. We will walk through the theory and basics of symbolic differentiation, and will implement two real world models: logistic regression and a deep net. A NumPy refresher will be given beforehand.
This talk is part of the Machine Learning Reading Group @ CUED series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|