Tech Showcase: Machine Teaching Using the Platform for Interactive Concept Learning (PICL)
Building machine learning (ML) models is an involved process requiring ML experts, engineers, and labelers. The demand of models for common-sense tasks far exceeds the available “teachers” that can build them. We approach this problem by allowing domain experts to apply what we call Machine Teaching (MT) principles. These include mining domain knowledge, concept decomposition, ideation, debugging, and semantic data exploration.
PICL is a toolkit that originated from the MT vision. It enables teachers with no ML expertise to build classifiers and extractors. The underlying SDK enables system designers and engineers to build customized experiences for their problem domain. In PICL, teachers can bring their own dataset, search or sample items to label using active learning strategies, label these items, create or edit features, monitor model performance, and review and debug errors, all in one place.
- Date:
- Speakers:
- Alicia Edelman Pelton, Johan Verwey
- Affiliation:
- Microsoft
-
-
Alicia Edelman Pelton
Principal Program Manager
-
Johan Verwey
Senior Research Software Engineer
-
-
Series: Microsoft Research Faculty Summit
-
-
Quantum Computing and Workforce, Curriculum, and Application Development: Case study
Speakers:- Krysta M. Svore,
- Martin Roetteler
-
-
-
-
Crowd, Cloud and the Future of Work: Updates from human AI computation
Speakers:- Besmira Nushi,
- Vani Mandava
-
-
-
-
-
Empowering People to Achieve More: How Useful a Concept is Productivity?
Speakers:- Brendan Murphy
-
-
Productivity in Software Development
Speakers:- Neel Sundaresan,
- Margaret-Anne Storey,
- Prem Kumar Devanbu
-
-
-
-
-
-
-
Accessible Virtual Reality
Speakers:- Eyal Ofek
-
Calendar.help: A Virtual Meeting Scheduling Assistant
Speakers:- Pamela Bhattacharya
-
Visual Studio IntelliCode
Speakers:- Mark Wilson-Thomas
-
Microsoft Teams: Collaborate with Any Researcher Anywhere
Speakers:- Jethro Seghers
-
Project Alava: Programming Webs of Microcontrollers
Speakers:- James Devine,
- Teddy Seyed
-
AI in PowerPoint
Speakers:- Kostas Seleskerov