Saturday 1:20 p.m.–4:40 p.m.
Diving into Machine Learning through TensorFlow
Julia Ferraioli, Amy Unruh, Eli Bixby
- Audience level:
- Intermediate
- Category:
- Science
Description
Machine learning can be an intimidating subject. In this session, we’ll get practical, hands-on experience with core concepts in machine learning with TensorFlow, an open source deep learning library. We’ll introduce the basics of TensorFlow, including how to ingest and prepare raw data for use, run a variety of algorithms to gain insight from the data, and have some fun with visualization.
Abstract
[TensorFlow][1]™ is an [open source software library][2] from Google for numerical computation using data flow graphs. It provides a flexible platform for defining and running machine learning algorithms, and is is particularly suited for neural net applications. In this workshop, we will use TensorFlow to define, train, and utilize a variety of machine learning algorithms on a number of datasets.
We will start by providing some background and motivation for problems in machine learning, and a brief history of the field, both from the perspective of Google, and the machine learning community as a whole. We’ll also give a brief overview of how Google uses TensorFlow in our services.
Next we’ll dive into an in-depth hands-on exploration of TensorFlow, in three parts:
1. Use pre-trained models for classification and regression on a variety of devices.
2. Scalably train models on a cluster, using algorithms bundled with the TensorFlow library, or defined by machine learning experts in the community -- such as stochastic gradient descent.
3. Implement some key machine learning algorithms in TensorFlow.
[1]: http://www.tensorflow.org/
[2]: https://github.com/tensorflow/tensorflow
Student Handout
No handouts have been provided yet for this tutorial
PyCon 2016 in Portland, OR is a production of the 