Learning with limited labeled data
Who is this presentation for?
- Data scientists, machine learning engineers, and product managers
Level
Description
Being able to teach machines with examples is a powerful capability, but it hinges on the availability of vast amounts of data. The data not only needs to exist but has to be in a form that allows relationships between input features and output to be uncovered. Creating labels for each input feature fulfills this requirement, but is an expensive undertaking.
Classical approaches to this problem rely on human and machine collaboration. In these approaches, engineered heuristics are used to smartly select “best” instances of data to label in order to reduce cost. A human steps in to provide the label; the model then learns from this smaller labeled dataset. Recent advancements have made these approaches amenable to deep learning, enabling models to be built with limited labeled data.
Shioulin Sam explores algorithmic approaches that drive this capability and provides practical guidance for translating this capability into production. You’ll view a live demonstration to understand how and why these algorithms work.
Prerequisite knowledge
- A basic understanding of math, classifiers, and neural networks
What you'll learn
- Learn classical active learning strategies (engineered heuristics) to choose the "best" data to label, active learning algorithms tailored for deep learning, an under-the-hood understanding of active learning, and when to use active learning and what to look out for
Shioulin Sam
Cloudera Fast Forward Labs
Shioulin Sam is a research engineer at Cloudera Fast Forward Labs, where she bridges academic research in machine learning with industrial applications. Previously, she managed a portfolio of early stage ventures focusing on women-led startups and public market investments and worked in the investment management industry designing quantitative trading strategies. She holds a PhD in electrical engineering and computer science from the Massachusetts Institute of Technology.
Comments on this page are now closed.
Presented by
Elite Sponsors
Strategic Sponsors
Zettabyte Sponsors
Contributing Sponsors
Exabyte Sponsors
Content Sponsor
Impact Sponsors
Supporting Sponsor
Non Profit
Contact us
confreg@oreilly.com
For conference registration information and customer service
partners@oreilly.com
For more information on community discounts and trade opportunities with O’Reilly conferences
strataconf@oreilly.com
For information on exhibiting or sponsoring a conference
pr@oreilly.com
For media/analyst press inquires
Comments
Link to presentation is here
Hi Shioulin
Is there anyway to get your awesome presentation?
Thanks, Bo
Is there a link to your great presentation?
Thanks, Gilad
Hi Shioulin
Do you have a link to your presentation?
Thanks