Interactive machine teaching
A human-centered approach to building machine-learned models
Bibliographic Data
| ID | 15215980 |
|---|---|
| Authors | Gonzalo Ramos (0000-0003-4198-5021, Microsoft Research, Redmond, WA, USA, corresponding author), Christopher Meek (0000-0003-1696-6152, Microsoft Research, Redmond, WA, USA), Patrice Simard (Microsoft), Jina Suh (0000-0002-7646-5563, Microsoft Research, Redmond, WA, USA), Soroush Ghorashi (Microsoft) |
| Year | 2020 |
| Volume | 35 |
| Issue | 5-6 |
| Pages | 413-451 |
| Publication date | 2020-04-30 |
| Open Access | No |
| Type | ARTICLE |
| Venue | Human-Computer Interaction (JOURNAL) |
| Journal identifiers | ISSN: 0737-0024 • E-ISSN: 1532-7051 |
| Publisher | Taylor & Francis (PUBLISHER • GB) |
| DOI | 10.1080/07370024.2020.1734931 |
| OpenAlex | W3023626240 |
| Language | EN |
| Citations received | 6 |
| References cited | 47 |
Modern systems can augment people’s capabilities by using machine-learned models to surface intelligent behaviors. Unfortunately, building these models remains challenging and beyond the reach of non-machine learning experts. We describe interactive machine teaching (IMT) and its potential to simplify the creation of machine-learned models. One of the key characteristics of IMT is its iterative process in which the human-in-the-loop takes the role of a teacher teaching a machine how to perform a task. We explore alternative learning theories as potential theoretical foundations for IMT, the intrinsic human capabilities related to teaching, and how IMT systems might leverage them. We argue that IMT processes that enable people to leverage these capabilities have a variety of benefits, including making machine learning methods accessible to subject-matter experts and the creation of semantic and debuggable machine learning (ML) models. We present an integrated teaching environment (ITE) that embodies principles from IMT, and use it as a design probe to observe how non-ML experts do IMT and as the basis of a system that helps us study how to guide teachers. We explore and highlight the benefits and challenges of IMT systems. We conclude by outlining six research challenges to advance the field of IMT
Expert system · Field (mathematics · Human–computer interaction · Human–machine system · Leverage (statistics · Machine learning · Process (computing · Subject-matter expert · Computer Science · Data Visualization and Analytics · Ethics and Social Impacts of AI · Explainable Artificial Intelligence (XAI · Artificial Intelligence
| Citations per year | 1.5 |
|---|---|
| Citation span | 2022 - 2025 (4) |
| Highly cited | No |