Abstract | ||
---|---|---|
This paper describes efficient concept acquisition for an infant agent (IA) based on learning biases that are observed in child language development. An IA acquires concepts through learning relations between visual features of objects and acoustic features of human speech. In this task, the IA has to find out which visual features are indicated by a speech. Previous concept acquisition systems find out them by using probabilistic methods, however, such approaches need much samples to achieve high accuracy. In this paper, firstly, we propose basic concept acquisition system using Online-EM algorithm without the biases. And then, we implement two types of learning biases to accelerate a learning process into our system. The experimental results show that the proposed method can achieve efficient learning. |
Year | Venue | Keywords |
---|---|---|
2006 | Artificial Intelligence and Applications | child development,efficient concept acquisition,child language development,acoustic feature,visual feature,human speech,previous concept acquisition system,online-em algorithm,basic concept acquisition system,efficient learning,concept learning,intelligent agents,symbol grounding |
Field | DocType | ISBN |
Intelligent agent,Semi-supervised learning,Active learning (machine learning),Computer science,Concept learning,Symbol grounding,Probabilistic method,Artificial intelligence,Language development,Machine learning,Knowledge acquisition | Conference | 0-88986-556-6 |
Citations | PageRank | References |
0 | 0.34 | 5 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ryo Taguchi | 1 | 33 | 8.10 |
Masashi Kimura | 2 | 0 | 1.35 |
Shuji Shinohara | 3 | 5 | 3.91 |
Kouichi Katsurada | 4 | 69 | 17.35 |
Tsuneo Nitta | 5 | 144 | 34.35 |