Advanced Machine Learning Tutorial

Event space and refreshments sponsored by: Thoughtworks (https://www.thoughtworks.com/locations/new-york)

Speaker: Andreas Mueller

Event agenda:

6:30pm - 7:00pm: Networking & Food

7:00pm - 9:00pm: Machine Learning, Grid Search Tutorial

9:00pm - 9:30pm: Networking

Description:

Scikit-learn is a machine learning library in Python which has become a valuable tool for many data science practitioners. This talk will cover some of the more advanced aspects of scikit-learn, such as building complex machine learning pipelines, model evaluation, parameter search, and out-of-core learning.

Apart from metrics for model evaluation, we will cover how to evaluate model complexity, and how to tune parameters with grid search, randomized parameter search, and what their trade-offs are. We will also cover out of core text feature processing via feature hashing.

The class will work in Python 2.7, 3.4 or 3.5. You’ll need the following packages (all included in Anaconda):

scikit-learn >= 0.16

matplotlib >= 1.3

numpy >= 1.5

IPython >= 4.0

Jupyter Notebook >= 4.0

These classification algorithms will be used: decision trees, random forests, linear SVM, kernel SVM.

Here’s a link to some reference machine learning IPython notebooks (https://github.com/amueller/odscon-sf-2015) on GitHub.

Preparation:

Please bring a laptop with Python installed, Anaconda (https://www.continuum.io/downloads) [Anaconda includes Jupyter] and Jupyter Notebook.

Prerequisites:

You should be comfortable with:

Python - at an intermediate level

Jupyter IPython notebook

Some background in machine learning is helpful but not required

Instructor Bio:

This workshop will be taught by Andreas Mueller. Andreas is an Assistant Research Scientist at the NYU Center for Data Science, building a group to work on open source software for data science. Previously he worked as a Machine Learning Scientist at Amazon, working on computer vision and forecasting problems. He is one of the core developers of the scikit-learn machine learning library, and has maintained it for several years.

His mission is to create open tools to lower the barrier of entry for machine learning applications, promote reproducible science and democratize the access to high-quality machine learning algorithms.

Andreas’ twitter: @amuellerml (https://twitter.com/amuellerml)

Andreas’ github: @amueller (https://github.com/amueller)