サンプリング手法が重要:ロボット言語獲得のための能動学習
Sampling Approach Matters: Active Learning for Robotic Language Acquisition
ロボットの言語獲得タスク3種に能動学習を適用し、データ選択手法が学習効率に与える影響を分析した研究。代表性と多様性を兼ね備えたサンプリングが重要であることを示した。
著者: Nisha Pillai, Edward Raff, Francis Ferraro, Cynthia Matuszek
分類: cs.RO, cs.CL, cs.LG
原文アブストラクト
Ordering the selection of training data using active learning can lead to improvements in learning efficiently from smaller corpora. We present an exploration of active learning approaches applied to three grounded language problems of varying complexity in order to analyze what methods are suitable for improving data efficiency in learning. We present a method for analyzing the complexity of data in this joint problem space, and report on how characteristics of the underlying task, along with design decisions such as feature selection and classification model, drive the results. We observe that representativeness, along with diversity, is crucial in selecting data samples.
