HVGH: Unsupervised Segmentation for High-Dimensional Time Series Using Deep Neural Compression and Statistical Generative Model

Humans perceive continuous high-dimensional information by dividing it into meaningful segments, such as words and units of motion. We believe that such unsupervised segmentation is also important for robots to learn topics such as language and motion. To this end, we previously proposed a hierarchi...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Front Robot AI
Hlavní autoři: Nagano, Masatoshi, Nakamura, Tomoaki, Nagai, Takayuki, Mochihashi, Daichi, Kobayashi, Ichiro, Takano, Wataru
Médium: Artigo
Jazyk:Inglês
Vydáno: Frontiers Media S.A. 2019
Témata:
Robotics and AI
On-line přístup:https://ncbi.nlm.nih.gov/pmc/articles/PMC7805757/
https://ncbi.nlm.nih.gov/pubmed/33501130
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.3389/frobt.2019.00115
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo otaguje tento záznam!

Podobné jednotky