AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Deep Network Approximation: Achieving Arbitrary Accuracy with Fixed Number of Neurons

Shijun Zhang, Zuowei Shen, Haizhao Yang

JMLR 2022 · Learning theory and algorithms › Sample complexity · approach: Hardness of learning neural networks · 24 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
replace ReLU by EUAF activation in a 4x80 fully connected networkFCNN1 · Function approximation (oscillatory 2D target)test MSE: 3.53e-5 -> 7.56e-6Improved
replace ReLU by EUAF in a 4x80 fully connected networkFCNN1 · Function approximation (oscillatory 2D target)test MAE: 4.57e-3 -> 2.13e-3Improved
replace ReLU by EUAF in a 4x80 fully connected networkFCNN1 · Function approximation (oscillatory 2D target)test MAX loss: 3.69e-2 -> 1.48e-2Improved
replace one channel or neuron per hidden layer of ReLU by EUAFCNN1 · Fashion-MNIST testaverage accuracy in last 100 epochs: 0.932698 -> 0.933508Improved
replace one channel or neuron per hidden layer of ReLU by EUAFCNN1 · Fashion-MNIST testlargest test accuracy: 0.933066 -> 0.933922Improved
replace one channel or neuron per hidden layer of ReLU by EUAFCNN1 · Fashion-MNIST testaverage of largest 100 accuracies: 0.932852 -> 0.933685Improved

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