AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Learning Deep ℓ0 Encoders

Zhangyang Wang, Qing Ling, Thomas Huang

AAAI 2016 · Architectures and efficiency › RNNs and normalization · approach: Differentiable optimization layers · 12 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 two-stage learned Deep ℓ0-Regularized Encoder instead of 10 iterative updatesℓ0 sparse code prediction · MNIST patches, ℓ0-regularized, p = 128, 256, 512prediction error (%): 3.55 -> 0.92; 4.33 -> 0.91; 4.08 -> 0.81Improved
Use a two-stage Deep M-Sparse Encoder instead of 10 iterative updatesM-sparse code prediction · MNIST patches, p = 128, 256, 512prediction error (%): 5.67 -> 2.94; 5.44 -> 2.87; 5.20 -> 3.29Improved
Use max_M pooling and unpooling to enforce the M-sparse supportDeep M-Sparse Encoder · MNIST patches, p = 128, 256, 512averaged non-zero support error: 4.6 -> 2.2; 5.6 -> 2.7; 5.3 -> 2.7Improved
Tune the enforced sparsity level to M = 20 rather than M = 10 or M = 30 (ablation)Deep M-Sparse Encoder · MNIST classification, p = 128, 256, 512classification error rate (%): 0.72 -> 0.69; 0.57 -> 0.54; 0.53 -> 0.51Improved
Set the enforced sparsity level to M = 10 rather than M = 20 or M = 30 (ablation)Deep M-Sparse Encoder · AVIRIS Indiana Pines classification, p = 128, 256, 512classification error rate (%): 14.67 -> 13.77; 14.23 -> 13.56; 14.07 -> 13.52Improved
Increase the number of unfolded stages from K = 2 to K = 3 or 4 (ablation)Deep ℓ0 encoders · Several tested casesperformanceImproved
Use Deep M-Sparse (M = 10) rather than Deep ℓ0-Regularized Encoder (ablation)Deep encoders · COIL 20 clustering, p = 512clustering error rate (%): 14.06 -> 14.03Improved
Use the learned-sparsity regularized encoder rather than hardcoding M (ablation)Deep encoders · CMU PIE clusteringclustering error rate (%): 15.41 vs 16.01Improved
Use Deep ℓ0 encoders rather than Tuned LISTAEnd-to-end sparse-code classification · MNIST and AVIRIS Indiana Pinesclassification error rate (%): MNIST p = 512: 0.57 -> 0.51; AVIRIS p = 512: 15.97 -> 13.52Mixed

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