原文传递
Using Convolutional Neural Networks to Extract Shift-Invariant Features from Unlabeled Data.
| 题名： | Using Convolutional Neural Networks to Extract Shift-Invariant Features from Unlabeled Data. |
| 作者： | Edwards , S.; Lee, M. S. |
| 关键词： | Unsupervised machine learning, Feature extraction, Coding, Decoding, Signal processing, Dimensionality reduction, Shift-invariant feature extraction, Unlabeled data, Convolutional what-where autoencoders, Dictionary learning |
| 摘要： | Unsupervised learning on limited data is a challenging task. In this work, we show that shallow what-where autoencoders, first developed as a pretraining tool for supervised classifiers, can also be used for shift-invariant feature extraction. Furthermore, feature vectors (i.e., the bottleneck layer activations), can be clustered to achieve unsupervised segmentation. In order to remove edge artifacts in the segmentation, overcoding is introduced, whereby the decoder only needs to reproduce a cropped version of the encoded signal. |
| 报告类型： | 科技报告 |
相关文献
- Evaluation of Using Deterministic Heuristics to Accelerate Reinforcement Learning.
- Predicting Adverse Events and their Precursors in Aviation Using Multi-Class Multiple-Instance Learning.
- PREDICTING TRAFFIC CONGESTION USING RECURRENT NEURAL NETWORKS.
- Linear Layers and Partial Weight Reinitialization for Accelerating Neural Network Convergence.
- EFFECT OF NOISY DATA ON PAVEMENT PERFORMANCE PREDICTION BY ARTIFICIAL NEURAL NETWORKS.
- Convolutional Neural Networks For Detection And Classification Of Maritime Vessels In Electro-Optical Satellite Imagery.
检索历史
应用推荐
