Meta-Parameter Free Unsupervised Sparse Feature Learning
| العنوان: | Meta-Parameter Free Unsupervised Sparse Feature Learning |
|---|---|
| المؤلفون: | Petia Radeva, Carlo Gatta, Adriana Romero |
| المصدر: | IEEE Transactions on Pattern Analysis and Machine Intelligence. 37:1716-1722 |
| بيانات النشر: | Institute of Electrical and Electronics Engineers (IEEE), 2015. |
| سنة النشر: | 2015 |
| مصطلحات موضوعية: | Computer Science::Machine Learning, Wake-sleep algorithm, business.industry, Computer science, Applied Mathematics, Competitive learning, Pattern recognition, Semi-supervised learning, Machine learning, computer.software_genre, Statistics::Machine Learning, Computational Theory and Mathematics, Discriminative model, Artificial Intelligence, Feature (computer vision), Encoding (memory), Unsupervised learning, Computer Vision and Pattern Recognition, Artificial intelligence, business, computer, Feature learning, Software |
| الوصف: | We propose a meta-parameter free, off-the-shelf, simple and fast unsupervised feature learning algorithm, which exploits a new way of optimizing for sparsity. Experiments on CIFAR-10, STL-10 and UCMerced show that the method achieves the state-of-the-art performance, providing discriminative features that generalize well. |
| تدمد: | 2160-9292 0162-8828 |
| DOI: | 10.1109/tpami.2014.2366129 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::de4f28124909658d3c82d7902e8afd4d https://doi.org/10.1109/tpami.2014.2366129 |
| Rights: | CLOSED |
| رقم الانضمام: | edsair.doi.dedup.....de4f28124909658d3c82d7902e8afd4d |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 21609292 01628828 |
|---|---|
| DOI: | 10.1109/tpami.2014.2366129 |