Loading...
Please wait, while we are loading the content...
Learning a nonlinear embedding by preserving class neighbourhood structure.
| Content Provider | CiteSeerX |
|---|---|
| Abstract | We show how to pretrain and fine-tune a multilayer neural network to learn a nonlinear transformation from the input space to a lowdimensional feature space in which K-nearest neighbour classification performs well. We also show how the non-linear transformation can be improved using unlabeled data. Our method achieves a much lower error rate than Support Vector Machines or standard backpropagation on a widely used version of the MNIST handwritten digit recognition task. If some of the dimensions of the low-dimensional feature space are not used for nearest neighbor classification, our method uses these dimensions to explicitly represent transformations of the digits that do not affect their identity. 1 |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Nonlinear Embedding Class Neighbourhood Structure Neighbor Classification Support Vector Machine Unlabeled Data Nonlinear Transformation Standard Backpropagation Low-dimensional Feature Space Non-linear Transformation Input Space Mnist Handwritten Digit Recognition Task K-nearest Neighbour Classification Performs Error Rate Multilayer Neural Network Lowdimensional Feature Space |
| Content Type | Text |
