Track: Deep Learning in Practice

Location: Embarcadero

Day of week: Tuesday

Deep learning uses multi-layered nonlinear processing units for feature extraction and transformation. While deep learning has been around in some form since 1986, recent advances in hardware, the sheer amount of available data, and algorithmic understanding have driven deep learning to the forefront. 

This track looks at some of the innovative applications of deep learning today. We'll explore using deep learning models to make recommendations on edge devices (protecting user data), explore how deep learning is being applied to search at places like Airbnb (use cases beyond image processing), the latest on explainability of machine learning models (understanding how models come to the answer they recommend), and, of course, image/perception algorithms. 

Deep learning is a rapidly evolving field. This track aims to update you on the latest trends shaping the field and pushing the industry forward.

Track Host: Mike Lee Williams

Research engineer @Cloudera Fast Forward Labs

Mike Lee Williams does applied research into computer science, statistics and machine learning at Cloudera Fast Forward Labs. While getting his PhD in astrophysics he spent 2% of his time observing the heavens in beautiful far west Texas, and the other 98% trying to figure out how to fit straight lines to data. He once did a postdoc at the Max Planck Institute for Extraterrestrial Physics, which, amazingly, is a real place.

10:40am - 11:20am

Applying Deep Learning To Airbnb Search

Searching for homes is the primary mechanism guests use to find the place they want to book at Airbnb. The goal of search ranking is to find guests the best possible options while rewarding the most deserving hosts. Ranking at Airbnb is a quest to understand the needs of the guests and the quality of the hosts to strike the best match possible. Applying machine learning to this challenge is one of the biggest success stories at Airbnb. Much of the initial gains were driven by a gradient boosted decision tree model. The gains, however, plateaued over time. This talk discusses the work done in applying neural networks in an attempt to break out of that plateau. The talk focuses on the elements we found useful in applying neural networks to a real life product. To other teams embarking on similar journeys, we hope this account of our struggles and triumphs will provide some useful pointers. Bon voyage!

Malay Haldar, Machine Learning Engineer @Airbnb

11:40am - 12:20pm

Deep Learning from a SWE's Perspective

Presentation details will follow soon.

Sravya Tirukkovalur, Senior Machine Learning Engineer @Adobe

1:20pm - 2:00pm

How to Make Great Personalization Private

Canopy is a privacy startup that believes that users should not have to give up their personal data in order to get good recommendations. And we're building a content discovery app to prove it. Come learn what a private recommendation stack looks like in 2019, and how to tackle issues like analytics, models updates and algorithmic fairness in a world where you want to know as little about your users as possible. 

Erica Greene, Machine Learning Engineer @ourcanopy

2:20pm - 3:00pm

Deep Learning in Practice panel

Panel details will follow soon.

3:20pm - 4:00pm

Deep Learning Presentation

Presentation details to follow.

4:20pm - 5:00pm

Deep Learning presentation

Each of the talks at QCon is individually curated and selected. Presentation details will follow soon.

2019 Tracks

  • Groking Timeseries & Sequential Data

    Techniques, practices, and approaches around time series and sequential data. Expect topics including image recognition, NLP/NLU, preprocess, & crunching of related algorithms.

  • Deep Learning in Practice

    Deep learning use cases around edge computing, deep learning for search, explainability, fairness, and perception.