AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Neural Network Architecture Beyond Width and Depth

Shijun Zhang, Zuowei Shen, Haizhao Yang

NeurIPS 2022 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 5 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 a trainable sub-network activation function (varrho) instead of ReLUNestNet versus standard network, width 20 and depth 4 · Archimedean spiral testtest accuracy: 0.738290 -> 0.873631Improved
Use a trainable sub-network activation function (varrho) instead of ReLUNestNet versus standard network, width 35 and depth 4 · Archimedean spiral testtest accuracy: 0.816048 -> 0.995962Improved
Use a trainable sub-network activation function (varrho) instead of ReLUNestNet versus standard network, width 50 and depth 4 · Archimedean spiral testtest accuracy: 0.866118 -> 0.999984Improved
Use sub-network activation varrho for a few CNN activations instead of ReLUCNN2 versus CNN1 · Fashion-MNIST testaverage accuracy in last 100 epochs: 0.924447 -> 0.926032Improved
Use sub-network activation varrho for a few CNN activations instead of ReLUCNN2 versus CNN1 · Fashion-MNIST trainingtraining time: ≈ 5802 s -> ≈ 7217 sHurt
Add nested architecture height s while keeping parameter count O(n)ReLU networks approximating 1-Lipschitz functions on [0,1]^d · 1-Lipschitz continuous functions on [0,1]^dapproximation error: n^{-2/d} -> n^{-(s+1)/d}Improved

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