Loading...
Please wait, while we are loading the content...
Similar Documents
Improving deep neural network performance by reusing features trained with transductive transference.
| Content Provider | CiteSeerX |
|---|---|
| Author | Sá, Joaquim Marques De |
| Abstract | Abstract. Transfer Learning is a paradigm in machine learning to solve a target problem by reusing the learning with minor modifications from a different but related source problem. In this paper we propose a novel feature transference approach, especially when the source and the target problems are drawn from different distributions. We use deep neural networks to transfer either low or middle or higher-layer features for a machine trained in either unsupervised or supervised way. Applying this feature transference approach on Convolutional Neural Network and Stacked Denoising Autoencoder on four different datasets, we achieve lower classification error rate with significant reduction in computation time with lower-layer features trained in supervised way and higher-layer features trained in unsupervised way for classifying images of uppercase and lowercase letters dataset. |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Transductive Transference Deep Neural Network Performance Higher-layer Feature Supervised Way Target Problem Classification Error Rate Different Distribution Convolutional Neural Network Different Datasets Related Source Problem Deep Neural Network Computation Time Lower-layer Feature Lowercase Letter Significant Reduction Minor Modification Transfer Learning Feature Transference Approach Stacked Denoising Autoencoder Machine Learning Unsupervised Way Novel Feature Transference Approach |
| Content Type | Text |
| Resource Type | Article |
