AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

A Theoretical Framework for Target Propagation

Alexander Meulemans, Francesco Carzaniga, Johan Suykens, João Sacramento, Benjamin F. Grewe

NeurIPS 2020 · Architectures and efficiency › RNNs and normalization · approach: Backprop-free credit assignment · 31 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 layer-wise reconstruction training with DRL for DTP feedback (ablation)DTP · MNISTtest error: 2.39 \pm 0.19\% -> 2.21 \pm 0.09\%Improved
Replace layer-wise reconstruction training with DRL for DTP feedback (ablation)DTP · Frozen-MNISTtest error: 10.64 \pm 0.53\% -> 6.10 \pm 0.17\%Improved
Replace layer-wise reconstruction training with DRL for DTP feedback (ablation)DTP · Fashion-MNISTtest error: 11.49 \pm 0.23\% -> 11.22 \pm 0.20\%Improved
Replace layer-wise reconstruction training with DRL for DTP feedback (ablation)DTP · CIFAR10test error: 51.74 \pm 0.30 \% -> 50.80 \pm 0.43 \%Improved
Add direct linear output-to-hidden feedback trained with DRL (ablation)DTP · MNIST, Frozen-MNIST, Fashion-MNIST, CIFAR10test error: 2.39 \pm 0.19\% -> 2.04 \pm 0.08\%; 10.64 \pm 0.53\% -> 6.42 \pm 0.17\%; 11.49 \pm 0.23\% -> 11.11 \pm 0.35\%; 51.74 \pmMixed
Use an output reconstruction loop without DRL difference correction (ablation)DDTP-linear · Frozen-MNISTtest error: 6.42 \pm 0.17\% -> 9.70 \pm 0.31\%Hurt
Use a random hidden feedback layer instead of direct linear feedback (ablation)DDTP-linear · Frozen-MNISTtest error: 6.42 \pm 0.17\% -> 5.11 \pm 0.19\%Improved
Use a random hidden feedback layer instead of direct linear feedback (ablation)DDTP-linear · CIFAR10test error: 50.36 \pm 0.26\% -> 51.94 \pm 0.49 \%Hurt
Pre-train DTP feedback weights (ablation)DTP · MNISTtest error: 2.39 \pm 0.19\% -> 2.26 \pm 0.18\%Improved
Pre-train DTP feedback weights (ablation)DTP · CIFAR10test error: 51.74 \pm 0.30 \% -> 52.20 \pm 0.50 \%Hurt
Add DRL-trained direct linear feedbackBP · CIFAR10, small CNNtest error: 24.38 \pm 0.29\% -> 23.99 \pm 0.31\%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