PyData Meetup - August 2016 - Apache SINGA + Statistical Efficiency

This is a past event

120 people went



• 6:45pm - 7:00pm Networking

• 7:00pm - 7:55pm Presentation: Introduction to Apache SINGA V1.0

Synopsis: SINGA is an Apache incubator project started since March 2015. 3 versions have been released with focus on distributed training of deep learning models. In this talk, we will share the architecture, programming model and examples of V1.0, which improves the usability and efficiency over V0.3. In particular, users can write C++ and Python code to train deep learning models. With the support of OpenCL, SINGA is able to run on Nvidia GPU and other hardware devices (e.g., AMD GPU and FPGA). Optimisations in terms of speed and memory management would also be discussed.

Speaker: Wei Wang is completing his Ph.D. in School of Computing, National University of Singapore. His research interests including deep learning systems and multi-modal data analysis. He is a committer of the SINGA project. .

• 8:00pm - 8:45pm Presentation: High Performance Machine Learning Models ­ A Practical Guide to Statistical Efficiency

Synopsis: Are you developing machine learning models for tasks such as medical diagnosis, algorithmic trading, or any other domain where accuracy and precision is critical? Have you already tried model ensembles / cross validation and other textbook methods, but still need to squeeze out more performance (in terms of accuracy) from your models? Do you work in a domain where data is hard to come by? If you answered yes to any of these questions, you need to figure out how to increase the statistical efficiency of your models. Statistical efficiency is a measure of model optimality ­ a more efficient model will need fewer observations than a less efficient model to achieve a given performance. This talk will present techniques to increase the statistical efficiency. These techniques are practical, battle­hardened and go beyond what is commonly found in typical textbooks.

Speaker: Shankar Satish is a Data Scientist at Manulife, where he builds machine learning and AI tools, platforms and teams for the firm’s insurance and asset management arms. He has a background in building data science and machine learning / AI systems for a variety of domains, including self driving / autonomous drones, IoT and e­commerce.

• 8:45pm - 8:50pm Lucky draw sponsored by O'Reilly


• New ebooks/videos from O'Reilly! Only for members attending the session!

Join us on Facebook and Twitter


Group Sponsor