Making Sense of Touch: Unsupervised Shapelet Learning in Bag-of-words Sense
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913681575510016 |
|---|---|
| author | Xian, Zhicong Chaudhary, Tabish Bock, Jürgen |
| author_facet | Xian, Zhicong Chaudhary, Tabish Bock, Jürgen |
| contents | This paper introduces NN-STNE, a neural network using t-distributed stochastic neighbor embedding (t-SNE) as a hidden layer to reduce input dimensions by mapping long time-series data into shapelet membership probabilities. A Gaussian kernel-based mean square error preserves local data structure, while K-means initializes shapelet candidates due to the non-convex optimization challenge. Unlike existing methods, our approach uses t-SNE to address crowding in low-dimensional space and applies L1-norm regularization to optimize shapelet length. Evaluations on the UCR dataset and an electrical component manipulation task, like switching on, demonstrate improved clustering accuracy over state-of-the-art feature-learning methods in robotics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_04167 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Making Sense of Touch: Unsupervised Shapelet Learning in Bag-of-words Sense Xian, Zhicong Chaudhary, Tabish Bock, Jürgen Machine Learning Robotics This paper introduces NN-STNE, a neural network using t-distributed stochastic neighbor embedding (t-SNE) as a hidden layer to reduce input dimensions by mapping long time-series data into shapelet membership probabilities. A Gaussian kernel-based mean square error preserves local data structure, while K-means initializes shapelet candidates due to the non-convex optimization challenge. Unlike existing methods, our approach uses t-SNE to address crowding in low-dimensional space and applies L1-norm regularization to optimize shapelet length. Evaluations on the UCR dataset and an electrical component manipulation task, like switching on, demonstrate improved clustering accuracy over state-of-the-art feature-learning methods in robotics. |
| title | Making Sense of Touch: Unsupervised Shapelet Learning in Bag-of-words Sense |
| topic | Machine Learning Robotics |
| url | https://arxiv.org/abs/2502.04167 |