CHI-ANNOUNCEMENTS Archives

ACM SIGCHI General Interest Announcements (Mailing List)

CHI-ANNOUNCEMENTS@LISTSERV.ACM.ORG

Options: Use Forum View

Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Kaushik Subramanian <[log in to unmask]>
Reply To:
Kaushik Subramanian <[log in to unmask]>
Date:
Thu, 7 Jul 2016 12:34:27 -0400
Content-Type:
text/plain
Parts/Attachments:
text/plain (58 lines)
Dear Colleagues,

You are cordially invited to participate in the "Interactive Machine Learning" workshop to be held at IJCAI 2016 in New York, USA this Saturday, July 9th, 2016. 
Room - Nassau East in the Hilton NY hotel.

The program can be found here: https://sites.google.com/site/ijcai2016iml/program

Workshop Overview
---------------------------------------------------------------------------------------

In recent years there has been an increased interest in the design of algorithms that facilitate machine learning with the help of human interaction. Such approaches often referred to as Interactive Machine Learning (IML), are based on a coupling of human input and machines during the learning process. Specifically IML is concerned with answering questions related to how machines can interact with people to solve problems more efficiently than autonomous systems (which often require intense engineering effort to be effective learning systems).

With the exponential growth in computing power and a focus on enhancing user-experience through technology, there exist several opportunities where humans are required to interact with machines to solve problems. Canonical applications of IML include scenarios involving humans interacting with robots to teach them to perform certain tasks, humans helping virtual agents play computer games by giving them feedback on their performance or using a teaching curriculum to guide the machine learning. However there exist a number of challenges in this area of research ranging from the choice of human interaction modality to the design of algorithms suitable for interactive learning and appropriate representations for the problem. As such these challenges span a variety of scientific disciplines and application domains like artificial intelligence, machine learning, human-computer interaction, cognitive science and robotics. The goal of the workshop is to bring together researchers in these fields to discuss the design and analysis of algorithms that facilitate Interactive Machine Learning. It is an opportunity for scientists in these disciplines to share their perspectives, discuss solutions to common problems and highlight the challenges in the field to help guide future research in IML.

Topics
---------------------------------------------------------------------------------------

- Supervised and semi-supervised learning
- Learning by demonstration and imitation learning
- Reinforcement learning with human interaction
- Interactive robot learning
- Active learning and preference learning
- Bayesian methods
- Personalized and teachable agents
- Transparency and feedback in ML
- Evaluation of interactive systems
- Intelligent interaction methodology
- Modeling people and their intentions
- Computational models of human teaching
- Multi-agent systems
- Human-in-the-loop intelligent systems

Invited Speakers
---------------------------------------------------------------------------------------

Maya Cakmak, University of Washington
Brenden Lake, New York University
Michael Littman, Brown University
Peter Stone, University of Texas at Austin

Organizers
---------------------------------------------------------------------------------------

Kaushik Subramanian, Georgia Institute of Technology
Heni Ben Amor, Arizona State University
Charles L. Isbell, Georgia Institute of Technology
Andrea L. Thomaz, Georgia Institute of Technology (now at University of Texas at Austin)

    ---------------------------------------------------------------
    For news of CHI books, courses & software, join CHI-RESOURCES
     mailto: [log in to unmask]

    To unsubscribe from CHI-ANNOUNCEMENTS send an email to
     mailto:[log in to unmask]

    For further details of CHI lists see http://listserv.acm.org
    ---------------------------------------------------------------

ATOM RSS1 RSS2