Recent advances in hardware, the sheer amount of available data, and algorithmic innovations have made deep learning one of the most active areas of machine learning research.
In "Deep Learning in Practice" we'll learn where those breakthroughs are making contact with the real world and production workloads. We'll explore deep learning applied rich and structured data for search at Aibrnb, distributed deep learning applied to private data, and learn how reinforcement learning is not just for robots and videogames.
We'll also hear a personal perspective on the relationship between production machine learning and mainstream software engineering based on a career at Cloudera, Adobe and fast.ai. And we'll acquire an arsenal of tools for debugging deep neural networks in use at Cardiogram.
There's a lot of hype around deep learning, and it's a rapidly evolving field. The Deep Learning in Practive track is a hand-picked selection of talks from industry experts about putting these ideas into practice in the real world.
Track: Deep Learning in Practice
Location: Cyril Magnin II
Day of week:

Track Host: Mike Lee Williams
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!
11:40am - 12:20pm
Reinforcement Learning: Not Just for Robots and Games
Reinforcement Learning (RL) and Deep Reinforcement Learning (DRL) has gained huge interests in recent years, as its application in solving very complicated strategy and decision-making problems, including DeepMind's AlphaGo, OpenAI Five, as well as autonomous driving and robotics. Though the technique itself is very powerful and promising, its applications outside of video games, robotics, and simulations are rare. As an "unusual" use case, Jibin will present one of his projects at eBay where the team used RL to improve crawling of targeted web pages. In this talk, we will start from the basics of RL, then to why and how to use it to power the web crawling. This talk is actually "casting a brick to attract jade", hoping to attract more ideas and applications of Reinforcement Learning from more fields.
1:20pm - 2:00pm
Machine Learning Engineering - A New Yet Not So New Paradigm
2:20pm - 3:00pm
Putting Fairness Principles Into Practice
3:20pm - 4:00pm
Debuggable Deep Learning
Deep Learning is often called a black box, so how can we diagnose and fix problems in a Deep Neural Network (DNN)? Engineers at Cardiogram explain how they systematically debugged DeepHeart, a DNN that detects cardiovascular disease from heart rate data. You'll leave this talk with an arsenal of tools for debugging DNNs, including Jacobian analysis, TensorBoard, and "DNN Unit Tests".
Avesh Singh, Software Engineer & Technical Lead @Cardiogram
4:20pm - 5:00pm
Federated Learning: Rewards & Challenges of Distributed Private ML
Federated Learning is a recent paradigm for machine learning that addresses user privacy concerns while also opening up orders of magnitude larger datasets for machine learning tasks by leaving data on user devices and pushing computation to the edge. In this talk, we will cover the basic concepts underlying the federated approach, the advantages it brings, as well as the machine learning and engineering challenges associated with constructing federated solutions. We will also focus on the use of federated learning for products in health and medicine, where successful implementations must pay special attention to privacy.
2019 Tracks
-
Hands-on Codelabs & Speakers Office Hours
Codelabs are a self-guided tutorial of a product, API, or tool kit followed by an Office Hour period with the lab’s creator.
-
Solving Software Engineering Problems with Machine Learning
Interesting machine learning use cases changing how we develop software today, including planned topics touching on infrastructure optimization, developer experience, security, and more.
-
Predictive Architectures in the Real World
Case Study focused look at end to end predictive pipelines from places like Salesforce, Uber, Linkedin, & Netflix.
-
Predictive Data Pipelines & Architectures
Case Study focused look at end to end predictive pipelines from places like Salesforce, Uber, Linkedin, & Netflix
-
Sequential Data: Natural Language, Time Series, and Sound
Techniques, practices, and approaches around time series and sequential data. Expect topics including image recognition, NLP/NLU, preprocess, & crunching of related algorithms.
-
ML in Action
Applied track demonstrating how to train, score, and handle common machine learning use cases, including heavy concentration in the space of security and fraud
-
Deep Learning in Practice
Deep learning use cases around edge computing, deep learning for search, explainability, fairness, and perception.
-
Handling Sequential Data Like an Expert / ML Applied to Operations
Discussing the complexities of time (half track) and Machine Learning in the data center (half track). Exploring topics from hyper loglog to predictive auto-scaling in each of two half-day tracks.
Half-day tracks -
AI Meets the Physical World
Where AI touches the physical world, think drones, ROS, NVidia, TPU and more.
-
Hands-on Codelabs & Speakers Office Hours
Codelabs are a self-guided tutorial of a product, API, or tool kit followed by an Office Hour period with the lab’s creator.
-
Papers in Production: Modern CS in the Real World
Groundbreaking papers make real-world impact.