Presented By O'Reilly and Cloudera
December 5-6, 2016: Training
December 6–8, 2016: Tutorials & Conference

Deep learning conference sessions

11:15am–11:55am Thursday, 12/08/2016
With the rise of deep learning, natural language understanding techniques are becoming more effective and are not as reliant on costly annotated data. This leads to an explosion of possibilities of what businesses can do with language. Alyona Medelyan explains what the newest NLU tools can achieve today and presents their common use cases.
9:00am–12:30pm Tuesday, 12/06/2016
Vartika Singh and Jayant Shekhar offers a hands-on tutorial that exposes you to techniques for building and tuning machine-learning apps using Spark ML libraries, building pipelines, tuning parameters, and graph processing with GraphX.
2:35pm–3:15pm Thursday, 12/08/2016
Deep learning has made a huge impact on predictive analytics and is here to stay, so you'd better get up to speed with the neural net craze. Mateusz Dymczyk explains why all the top companies are using deep learning, what it's all about, and how you can start experimenting and implementing deep learning solutions in your business in only a few easy steps.
5:05pm–5:45pm Thursday, 12/08/2016
Ever wondered how Google Translate works so well, how the autocaptioning works on YouTube, or how to mine the sentiments of tweets on Twitter? What’s the underlying theme? They all use deep learning. Bargava Subramanian and Amit Kapoor explore artificial neural networks and deep learning for natural language processing to get you started.
1:30pm–5:00pm Tuesday, 12/06/2016
Wolff Dobson walks you through training and deploying a machine-learning system using TensorFlow, a popular open source library, and demonstrates how to build machine-learning systems from simple classifiers to complex image-based models.
4:15pm–4:55pm Thursday, 12/08/2016
Adam Gibson offers a brief overview of deep reinforcement learning on Spark, exploring how to run large-scale training on Spark and the implications on deep reinforcement learning targeting the doom environment.
12:05pm–12:45pm Wednesday, 12/07/2016
Verdi March demystifies deep learning and shares his experience on how to gradually transition to deep learning. Using a specific example in computer vision, Verdi touches upon key differences in engineering traditional software versus deep learning-based software.
2:35pm–3:15pm Wednesday, 12/07/2016
Nir Lotan describes a new, free software tool based on existing deep learning frameworks that enables the fast and easy creation of deep learning models and incorporates extensive optimizations that provide high performance on standard CPUs.
1:45pm–2:25pm Thursday, 12/08/2016
When operating on billions of data events per day, modern AI and machine-learning programs require distributed clusters with tens to hundreds machines. Qirong Ho offers an introduction to high-efficiency AI and ML distributed systems developed as part of the Petuum open source project and explains how they can reduce capital and operational costs for businesses.
2:35pm–3:15pm Thursday, 12/08/2016
Interested in optimizing speed and performance for machine learning and artificial intelligence applications or current research trends in machine learning and artificial intelligence? Meet with Qirong.
10:00am–10:15am Wednesday, 12/07/2016
Machine learning and artificial intelligence show great promise, but, really, machine learning and deep learning are already here and being used everywhere around you. Find out how Google uses large-scale machine learning in many of its products, and how TensorFlow and ML can help your business (and even help you make art and music).
4:15pm–4:55pm Thursday, 12/08/2016
Anusua Trivedi proposes a method to apply a pretrained deep convolution neural network (DCNN) on images to improve prediction accuracy. This approach improves prediction accuracy on domain-specific image datasets compared to state-of-the-art machine-learning approaches.
11:15am–11:55am Thursday, 12/08/2016
Jason Dai and Yiheng Wang share their experience building web-scale machine learning using Apache Spark—focusing specifically on "war stories" (e.g., in-game purchase, fraud detection, and deep leaning)—outline best practices to scale these learning algorithms, and discuss trade-offs in designing learning systems for the Spark framework.