Probabilistic Implicit Multitask Feature Learning Based on Weight Matrix Partition

Existing research suggests that adults and older children experience a tradeoff where instruction and feedback help them solve a problem efficiently, but lead them to ignore currently irrelevant information that might be useful in the future. It is unclear whether young children experience the same tradeoff. Eighty-seven children (ages five- to eight-years) and 42 adults participated in supervised feature prediction tasks either with or without an instructional hint. Follow-up tasks assessed learning of feature correlations and feature frequencies. Younger children tended to learn frequencies of both relevant and irrelevant features without instruction, but not the diagnostic feature correlation needed for the prediction task. With instruction, younger children did learn the diagnostic feature correlation, but then failed to learn the frequencies of irrelevant features. Instruction helped older children learn the correlation without limiting attention to frequencies. Adults learned the diagnostic correlation even without instruction, but with instruction no longer learned about irrelevant frequencies. These results indicate that young children do show some costs of learning with instruction characteristic of older children and adults. However, they also receive some of the benefits. The current study illustrates just what those tradeoffs might be, and how they might change over development.

Download Full-text

ResNet Autoencoders for Unsupervised Feature Learning From High-Dimensional Data: Deep Models Resistant to Performance Degradation

IEEE Access ◽

10.1109/access.2021.3064819 ◽

2021 ◽

Vol 9 ◽

pp. 40511-40520

Author(s):

Chathurika S. Wickramasinghe ◽

Daniel L. Marino ◽

Milos Manic

Keyword(s):

High Dimensional Data ◽

Feature Learning ◽

Performance Degradation ◽

High Dimensional ◽

Unsupervised Feature Learning

Download Full-text

Joint Deep Networks based Multi-source Feature Learning for QoS Prediction

IEEE Transactions on Services Computing ◽

10.1109/tsc.2021.3050178 ◽

2021 ◽

pp. 1-1

Author(s):

Youhao Xia ◽

Ding Ding ◽

Zhenhua Chang ◽

Fan Li

Keyword(s):

Feature Learning ◽

Qos Prediction ◽

Deep Networks

Download Full-text

Construction of a deep sparse filtering network for rotating machinery fault diagnosis

Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering ◽

10.1177/09544070211014852 ◽

2021 ◽

pp. 095440702110148

Author(s):

Chun Cheng ◽

Wei Zou ◽

Weiping Wang ◽

Michael Pecht

Keyword(s):

Fault Diagnosis ◽

Back Propagation ◽

Feature Learning ◽

Back Propagation Neural Network ◽

Rotating Machinery ◽

Fine Tuning ◽

Local Optimum ◽

Back Propagation Algorithm ◽

Intelligent Fault Diagnosis ◽

Sparse Filtering

Deep neural networks (DNNs) have shown potential in intelligent fault diagnosis of rotating machinery. However, traditional DNNs such as the back-propagation neural network are highly sensitive to the initial weights and easily fall into the local optimum, which restricts the feature learning capability and diagnostic performance. To overcome the above problems, a deep sparse filtering network (DSFN) constructed by stacked sparse filtering is developed in this paper and applied to fault diagnosis. The developed DSFN is pre-trained by sparse filtering in an unsupervised way. The back-propagation algorithm is employed to optimize the DSFN after pre-training. Then, the DSFN-based intelligent fault diagnosis method is validated using two experiments. The results show that pre-training with sparse filtering and fine-tuning can help the DSFN search for the optimal network parameters, and the DSFN can learn discriminative features adaptively from rotating machinery datasets. Compared with classical methods, the developed diagnostic method can diagnose rotating machinery faults with higher accuracy using fewer training samples.

Download Full-text

Cluster-Wise Weighted NMF for Hyperspectral Images Unmixing with Imbalanced Data

Remote Sensing ◽

10.3390/rs13020268 ◽

2021 ◽

Vol 13 (2) ◽

pp. 268

Author(s):

Xiaochen Lv ◽

Wenhong Wang ◽

Hongfu Liu

Keyword(s):

Spatial Information ◽

Hyperspectral Image ◽

Imbalanced Data ◽

Reconstruction Error ◽

Hyperspectral Data ◽

Weight Matrix ◽

Hyperspectral Images ◽

Mixed Data ◽

Sparsity Constraints ◽

Additional Constraints

Hyperspectral unmixing is an important technique for analyzing remote sensing images which aims to obtain a collection of endmembers and their corresponding abundances. In recent years, non-negative matrix factorization (NMF) has received extensive attention due to its good adaptability for mixed data with different degrees. The majority of existing NMF-based unmixing methods are developed by incorporating additional constraints into the standard NMF based on the spectral and spatial information of hyperspectral images. However, they neglect to exploit the nature of imbalanced pixels included in the data, which may cause the pixels mixed with imbalanced endmembers to be ignored, and thus the imbalanced endmembers generally cannot be accurately estimated due to the statistical property of NMF. To exploit the information of imbalanced samples in hyperspectral data during the unmixing procedure, in this paper, a cluster-wise weighted NMF (CW-NMF) method for the unmixing of hyperspectral images with imbalanced data is proposed. Specifically, based on the result of clustering conducted on the hyperspectral image, we construct a weight matrix and introduce it into the model of standard NMF. The proposed weight matrix can provide an appropriate weight value to the reconstruction error between each original pixel and the reconstructed pixel in the unmixing procedure. In this way, the adverse effect of imbalanced samples on the statistical accuracy of NMF is expected to be reduced by assigning larger weight values to the pixels concerning imbalanced endmembers and giving smaller weight values to the pixels mixed by majority endmembers. Besides, we extend the proposed CW-NMF by introducing the sparsity constraints of abundance and graph-based regularization, respectively. The experimental results on both synthetic and real hyperspectral data have been reported, and the effectiveness of our proposed methods has been demonstrated by comparing them with several state-of-the-art methods.

Download Full-text