AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Improving Anytime Prediction with Parallel Cascaded Networks and a Temporal-Difference Loss

Michael Louis Iuzzolino, Michael Curtis Mozer, Samy Bengio

NeurIPS 2021 · Architectures and efficiency › RNNs and normalization · approach: Brain-inspired network comparison · 2 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 TD(λ) with λ below 1 rather than TD(1) (ablation)Cascaded ResNet · CIFAR-100accuracy: 63.20 ± 0.14 -> 67.48 ± 0.14Improved
Use TD(λ) with λ below 1 rather than TD(1) (ablation)Cascaded ResNet · CIFAR-10accuracy: 88.75 ± 0.42 -> 91.65 ± 0.08Improved
Use TD(λ) with λ below 1 rather than TD(1) (ablation)Cascaded ResNet · TinyImageNetaccuracy: 49.86 ± 0.15 -> 52.25 ± 0.07Improved
Add TD(0) training instead of standard cross-entropy training (ablation)Cascaded ResNet · CIFAR-100accuracy: 65.56 ± 0.06 -> 67.48 ± 0.14Improved
Add TD(0) training instead of standard cross-entropy training (ablation)Cascaded ResNet · CIFAR-10accuracy: 91.91 ± 0.08 -> 91.22 ± 0.18Hurt
Add TD(0) training instead of standard cross-entropy training (ablation)Cascaded ResNet · TinyImageNetaccuracy: 52.46 ± 0.06 -> 50.74 ± 0.11Hurt
Use the cascaded architecture with TD training rather than the serial SDN-style modelAnytime image classification · CIFAR-10, CIFAR-100, TinyImageNetspeed-accuracy trade-offImproved
Use multi-head instead of shared-head readouts (ablation)Serial anytime model · CIFAR-10, CIFAR-100, TinyImageNetspeed-accuracy trade-offImproved
Use multi-head instead of shared-head readouts (ablation)Cascaded anytime model · CIFAR-10, CIFAR-100, TinyImageNetspeed-accuracy trade-offHurt
Train with TD rather than standard cross-entropy (ablation)Cascaded model · CIFAR-10 prototypicalitySpearman correlation with negative selection latency: 0.140 -> 0.352; 0.326 -> 0.489; 0.153 -> 0.142Mixed
Train CascadedTD instead of CascadedCE (ablation)Cascaded ResNet · CIFAR-10 persistent lossy noiseasymptotic accuracy (%): 83.75 ± 0.10 -> 87.31 ± 0.04; 82.73 ± 0.09 -> 89.76 ± 0.05; 84.56 ± 0.05 -> 87.67 ± 0.08; 85.40 ± 0.07 -> 88.19 ± 0.10Improved
Train CascadedTD instead of CascadedCE (ablation)Cascaded ResNet · CIFAR-10 transient lossy noisedrop in integrated performance: 0.66 ± 0.05 -> 0.00 ± 0.01; 8.25 ± 0.72 -> 0.93 ± 0.15; 0.87 ± 0.07 -> 0.00 ± 0.01; 0.53 ± 0.05 -> 0.18 ± 0.02Improved

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