Research map / Architectures and efficiency / RNNs and normalization
AutoNet-Generated Deep Layer-Wise Convex Networks for ECG Classification
Yanting Shen, Lei Lü, Tingting Zhu, Xinshao Wang, Lei Clifton, Zhengming Chen, Robert Clarke, David Andrew Clifton
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 Leaky-LCN instead of Hannun-Rajpurkar ResNet | AutoNet-LCN · ICBEB | 9-class F1: 75.9 -> 77.6 | Improved |
| use ReLU-LCN instead of Hannun-Rajpurkar ResNet | AutoNet-LCN · ICBEB | 9-class F1: 75.9 -> 75.6 | No clear effect |
| use LCN with 2.3% of the parameters | ReLU-LCN / Leaky-LCN · ICBEB | runtime: 1,911 -> 955 | Improved |
| use ReLU-LCN instead of Hannun-Rajpurkar | AutoNet-LCN · CKB | 4-class F1: 68.9 -> 77.2 | Improved |
| use Leaky-LCN instead of Hannun-Rajpurkar | AutoNet-LCN · CKB | 4-class F1: 68.9 -> 75.8 | Improved |
| use Leaky-LCN instead of Hannun-Rajpurkar | AutoNet-LCN · PhysioNet 2017 | F1 (4-class): 78.5 -> 83.3 | Improved |
| use ReLU-LCN instead of Hannun-Rajpurkar | AutoNet-LCN · PhysioNet 2017 | F1 (F13): 79.8 -> 80.5 | No clear effect |
| use Leaky-LCN instead of ReLU-LCN | AutoNet-LCN · Spoken Arabic Digits | 10-class F1: 98.8 -> 99.3 | Improved |
| use Leaky-LCN instead of ReLU-LCN | AutoNet-LCN · Face Detection | 2-class F1: 66.8 -> 67.7 | Improved |
| use Leaky-LCN instead of ReLU-LCN | AutoNet-LCN · CKB | 4-class F1: 77.2 -> 75.8 | No clear effect |
| use AutoNet-LCN instead of large transformers | AutoNet-LCN · Spoken Arabic Digits | parameters: 6,780,426 -> 334,098 | Improved |
| use AutoNet-LCN instead of TimesNet | AutoNet-LCN · Face Detection | accuracy: 68.6 -> 67.7 | No clear effect |
Closest papers by meaning
- Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners (ICML 2025 · similarity 0.84)
- From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining (ICML 2025 · similarity 0.83)
- Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model (ICLR 2025 · similarity 0.82)
- Parallel-Learning of Invariant and Tempo-variant Attributes of Single-Lead Cardiac Signals: PLITA (AAAI 2025 · similarity 0.82)
- Robustness and Visual Explanation for Black Box Image, Video, and ECG Signal Classification with Reinforcement Learning (AAAI 2024 · similarity 0.82)
- Extending Pretrained 10-Second ECG Foundation Models to Longer Horizons (NeurIPS 2026 · similarity 0.82)
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.
