As Intelligent Personal Assistants (IPA) such as Apple Siri, Google
Now, Microsoft Cortana, and Amazon Echo continue to gain traction,
webservice companies are now providing image, speech, and natural
language processing web services as the core applications in their
datacenters. These emerging applications require machine learning
and are known to be significantly more compute intensive than
traditional cloud based web services, giving rise to a number of
questions surrounding the designs of server and datacenter
architectures for handling this volume of computation.
Lucida is the next generation of Sirius, the first open source intelligent personal assistant that was developed by Clarity Lab at the University of Michigan.
Lucida is a speech and vision based intelligent personal assistant developed in Clarity Lab at the University of Michigan. It is a state-of-the-art infrastructures to study emerging intelligent web services in large scale systems. This website includes a tutorial to help you familiarize with the algorithms, implementations and characteristics of these workloads. The first half of the tutorial covers the machine learning and other algorithmic components underlying modern intelligent web services. In the second half of the tutorial, we discuss the Sirius and DjiNN benchmark suites: 13 web services that span image, speech, and natural language processing applications. We discuss the design of these applications as well as how they can be used to study the design of future datacenter architectures.