Budgeted Interactive Learning

Abstract

This project had two questions it was seeking to answer: how to enrich the protocols for interactive learning?, and how to properly make multi-criteria decisions during the interactive learning process? Towards answering the first question, the PI's team broke it into three subareas:(1) protocols that combine the benefits of online and batch learning, (2) protocols that improve interactive learning with other sources of information, and (3) protocols that allow extracting useful representations during interactive learning. Aligned with the three subareas, they have designed algorithms that allow selecting active learning approaches on the fly (for 2) and transferring the selection experience to other active learning tasks (for 1, 2, and 3). The selection scheme is implemented and released as an open-source active learning package. They have studied theories for designing algorithms for interactive learning with batch-like feedback (for 1) and algorithms for online digestion of representation (for 1 and 3). The team has also addressed real-world needs for considering concept drift during online learning (for 2) and utilizing costs during deep learning, multi-label learning and active learning (for 2 and 3). For the second question, the PI's team has seen promising results on (4) the annotation-budget-sensitive active learning, (5) rethinking deep learning models that trade training/prediction time with performance in large-scale learning, and (6) label embedding models that trade time (embedding length) with performance.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 15, 2017
Accession Number
AD1043682

Entities

People

  • Hsuan-Tien Lin

Organizations

  • National Taiwan University

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Air Force Research Laboratories
  • Algorithms
  • Artificial Intelligence
  • Artificial Intelligence Software
  • Convolutional Neural Networks
  • Data Mining
  • Data Sets
  • Deep Learning
  • Dimensionality Reduction
  • Distance Learning
  • Information Science
  • Machine Learning
  • Neural Networks
  • Recurrent Neural Networks
  • Reinforcement Learning
  • Training

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Neural Network Machine Learning.
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks