dc.citation.conferencePlace |
AT |
- |
dc.citation.conferencePlace |
Sydney |
- |
dc.citation.endPage |
586 |
- |
dc.citation.startPage |
577 |
- |
dc.citation.title |
International Conference on Knowledge Discovery and Data Mining |
- |
dc.contributor.author |
Kim, Taehwan |
- |
dc.contributor.author |
Taylor, Sarah |
- |
dc.contributor.author |
Yue, Yisong |
- |
dc.contributor.author |
Matthews, Iain |
- |
dc.date.accessioned |
2023-12-19T22:08:08Z |
- |
dc.date.available |
2023-12-19T22:08:08Z |
- |
dc.date.created |
2021-09-01 |
- |
dc.date.issued |
2015-08 |
- |
dc.description.abstract |
We study the problem of learning to predict a spatiotemporal output sequence given an input sequence. In contrast to conventional sequence prediction problems such as part-of-speech tagging (where output sequences are selected using a relatively small set of discrete labels), our goal is to predict sequences that lie within a high-dimensional continuous output space. We present a decision tree framework for learning an accurate non-parametric spatiotemporal sequence predictor. Our approach enjoys several attractive properties, including ease of training, fast performance at test time, and the ability to robustly tolerate corrupted training data using a novel latent variable approach. We evaluate on several datasets, and demonstrate substantial improvements over existing decision tree based sequence learning frameworks such as SEARN and DAgger. |
- |
dc.identifier.bibliographicCitation |
International Conference on Knowledge Discovery and Data Mining, pp.577 - 586 |
- |
dc.identifier.doi |
10.1145/2783258.2783356 |
- |
dc.identifier.issn |
0000-0000 |
- |
dc.identifier.scopusid |
2-s2.0-84954136808 |
- |
dc.identifier.uri |
https://scholarworks.unist.ac.kr/handle/201301/53839 |
- |
dc.language |
영어 |
- |
dc.publisher |
Association for Computing Machinery |
- |
dc.title |
A decision tree framework for spatiotemporal sequence prediction |
- |
dc.type |
Conference Paper |
- |
dc.date.conferenceDate |
2015-08-10 |
- |