AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

SVM-Based Deep Stacking Networks

Jingyuan Wang, Kai Feng, Junjie Wu

AAAI 2019 · Architectures and efficiency › RNNs and normalization · approach: Representation geometry and collapse · 42 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use SVM-DSN instead of DSN3-layer deep stacking model · MNISTError Rate (%): 1.65 -> 1.49Improved
Use BLT instead of BP to train the SVM-DSN structure (ablation)3-layer SVM-DSN · MNISTError Rate (%): 1.62 -> 1.49Improved
Use CNN + SVM-DSN instead of CNN + DSNCNN feature extractor with a 3-layer deep stack · MNIST with CNN feature extractorError Rate (%): 0.60 -> 0.51Improved
Use BLT instead of BP to train the SVM-DSN part (ablation)CNN + SVM-DSN · MNIST with CNN feature extractorError Rate (%): 0.72 -> 0.51Improved
Use SVM-DSN instead of DSNDeep stacking model · IMDBError Rate (%): 11.15 -> 10.51Improved
Use BLT instead of BP to train the SVM-DSN structure (ablation)SVM-DSN · IMDBError Rate (%): 11.42 -> 10.51Improved
Use SVM-DSN instead of stacking strong base learnersStacking model · IMDBError Rate (%): 11.55 -> 10.51Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy