September 26-27, 2016
New York, NY

Deeply active learning: Approximating human learning with smaller datasets combined with human assistance

Christopher Nguyen (Arimo), Binh Han (Arimo)
1:30pm–2:10pm Monday, 09/26/2016
Interacting with AI
Location: 3D09 Level: Intermediate
Average rating: ***..
(3.00, 1 rating)

What you'll learn

  • Learn how active learning combined with deep learning can speed up "time to AI," increasing the level of effectiveness a smart assistant can achieve for a given amount of training data
  • Description

    Natural-language assistants are the emergent killer app for AI. An important use case is mapping natural-language questions to answers, expressed as a sequence of API calls. A business user wants to ask for some analysis, but traditional user interface systems create some affordances for business users to do some predefined set of operations by hard-wiring UI events to application-level APIs, severely limiting business users to phrasing their requests in very mechanical, well-formed, and fixed interactions (choosing options, clicking buttons, filling out wizards, etc.).

    Deep learning (specifically recurrent neural networks), on the other hand, shows surprisingly good performance on text understanding and natural language processing. By taking advantage of recurrent networks, we can create a smart assistant that knows plain English out of the box and can map English phrases to API calls. However, getting from here to there can require enormous datasets.

    Christopher Nguyen and Binh Han explain how to shorten the time to effectiveness and the amount of training data that’s required to achieve a given level of performance using human-in-the-loop active learning. By using the smart assistant model, Chistopher and Binh allow the assistant to actively learn over time by simply interacting with a user. Active learning gradually pushes the pretrained general deep model underneath toward a customized model that responds much better to the user requests—a personalized smart assistant that can adapt to users’ styles.

    Photo of Christopher Nguyen

    Christopher Nguyen

    Arimo

    Christopher Nguyen is president and CEO of Arimo, a Panasonic company in Silicon Valley, where he leads the development of AI platforms and solutions for the enterprise. Previously, he was engineering director of Google Apps and cofounded two other successful startups. As a professor, Christopher cofounded the Computer Engineering Program at HKUST. He holds a BS (summa cum laude) from the University of California, Berkeley, and a PhD from Stanford, where he created the first standard-encoding Vietnamese software suite, authored RFC 1456, and contributed to Unicode 1.1.

    Photo of Binh Han

    Binh Han

    Arimo

    Binh Han is a senior software engineer and data scientist at Arimo, a leader in building the enterprise brain, where she focuses on building its machine learning platform, with a focus on deep learning. Previously, Binh held multiple software engineering and research positions involving big data analytics. She has authored and coauthored numerous publications and presentations on scientific computing, spatiotemporal data mining, and distributed systems. Binh holds a PhD in computer science from Georgia Tech.