AI Paper Atlas

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

TPAMI 2024 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 10 citations (OpenAlex)

Read the paper

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 Leaky-LCN instead of Hannun-Rajpurkar ResNetAutoNet-LCN · ICBEB9-class F1: 75.9 -> 77.6Improved
use ReLU-LCN instead of Hannun-Rajpurkar ResNetAutoNet-LCN · ICBEB9-class F1: 75.9 -> 75.6No clear effect
use LCN with 2.3% of the parametersReLU-LCN / Leaky-LCN · ICBEBruntime: 1,911 -> 955Improved
use ReLU-LCN instead of Hannun-RajpurkarAutoNet-LCN · CKB4-class F1: 68.9 -> 77.2Improved
use Leaky-LCN instead of Hannun-RajpurkarAutoNet-LCN · CKB4-class F1: 68.9 -> 75.8Improved
use Leaky-LCN instead of Hannun-RajpurkarAutoNet-LCN · PhysioNet 2017F1 (4-class): 78.5 -> 83.3Improved
use ReLU-LCN instead of Hannun-RajpurkarAutoNet-LCN · PhysioNet 2017F1 (F13): 79.8 -> 80.5No clear effect
use Leaky-LCN instead of ReLU-LCNAutoNet-LCN · Spoken Arabic Digits10-class F1: 98.8 -> 99.3Improved
use Leaky-LCN instead of ReLU-LCNAutoNet-LCN · Face Detection2-class F1: 66.8 -> 67.7Improved
use Leaky-LCN instead of ReLU-LCNAutoNet-LCN · CKB4-class F1: 77.2 -> 75.8No clear effect
use AutoNet-LCN instead of large transformersAutoNet-LCN · Spoken Arabic Digitsparameters: 6,780,426 -> 334,098Improved
use AutoNet-LCN instead of TimesNetAutoNet-LCN · Face Detectionaccuracy: 68.6 -> 67.7No clear effect

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