Research map / Architectures and efficiency / RNNs and normalization
SVM-Based Deep Stacking Networks
Jingyuan Wang, Kai Feng, Junjie Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use SVM-DSN instead of DSN | 3-layer deep stacking model · MNIST | Error Rate (%): 1.65 -> 1.49 | Improved |
| Use BLT instead of BP to train the SVM-DSN structure (ablation) | 3-layer SVM-DSN · MNIST | Error Rate (%): 1.62 -> 1.49 | Improved |
| Use CNN + SVM-DSN instead of CNN + DSN | CNN feature extractor with a 3-layer deep stack · MNIST with CNN feature extractor | Error Rate (%): 0.60 -> 0.51 | Improved |
| Use BLT instead of BP to train the SVM-DSN part (ablation) | CNN + SVM-DSN · MNIST with CNN feature extractor | Error Rate (%): 0.72 -> 0.51 | Improved |
| Use SVM-DSN instead of DSN | Deep stacking model · IMDB | Error Rate (%): 11.15 -> 10.51 | Improved |
| Use BLT instead of BP to train the SVM-DSN structure (ablation) | SVM-DSN · IMDB | Error Rate (%): 11.42 -> 10.51 | Improved |
| Use SVM-DSN instead of stacking strong base learners | Stacking model · IMDB | Error Rate (%): 11.55 -> 10.51 | Improved |
Closest papers by meaning
- Learning from Few Samples: Transformation-Invariant SVMs with Composition and Locality at Multiple Scales (NeurIPS 2022 · similarity 0.82)
- Greedy Layerwise Learning Can Scale To ImageNet (ICML 2019 · similarity 0.82)
- AutoBSS: An Efficient Algorithm for Block Stacking Style Search (NeurIPS 2020 · similarity 0.82)
- Diving into the shallows: a computational perspective on large-scale shallow learning (NeurIPS 2017 · similarity 0.81)
- LORS: Low-rank Residual Structure for Parameter-Efficient Network Stacking (CVPR 2024 · similarity 0.81)
- Deep Support Vectors (NeurIPS 2024 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
