AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Reinforcing Neural Network Stability with Attractor Dynamics

Hanming Deng, Yang Hua, Tao Song, Zhengui Xue, Ruhui Ma, Neil Robertson, Haibing Guan

AAAI 2020 · Probabilistic and scientific modeling › Dynamical systems · approach: Stable contractive dynamics · 4 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
add RMAN with 256 placement attractors (ablation)ResNet-44 · CIFAR100test error (%): 28.16 -> 27.57Improved
add RMAN with 256 placement attractors (ablation)ResNext-29 (8x64d) · CIFAR100test error (%): 19.59 -> 18.22Improved
add RMAN with 256 placement attractors (ablation)LM-ResNet-110 · CIFAR100test error (%): 25.46 -> 24.36Improved
add RMAN with 256 placement attractors (ablation)ResNet-20 · CIFAR10test error (%): 7.95 -> 7.68Improved
add RMAN with 16 placement attractors (ablation)ResNet-44 · CIFAR100test error (%): 28.16 -> 27.87Improved
add RMAN with 64 placement attractors (ablation)ResNet-44 · CIFAR100test error (%): 28.16 -> 28.02No clear effect
vary number of placement attractors from 16 to 256 (ablation)RMAN · CIFAR10/CIFAR100test error (%)No clear effect
add RMAN to Neural ODE (8 attractors) (ablation)ODE-Net · CIFAR10test error (%): 12.09 -> 11.64Improved
add RMAN to Neural ODE (16 attractors) (ablation)ODE-Net · CIFAR100test error (%): 41.06 -> 40.54Improved
add RMAN to Neural ODE (8 attractors) (ablation)ODE-Net · CIFAR10NFE: 26.3 -> 32.4Improved
add RMAN with 256 placement attractors (ablation)ResNet-34 · Google Commandstest error (%): 4.02 -> 3.78Improved
add RMAN with 256 placement attractors (ablation)ResNet-18 · Google Commandstest error (%): 4.06 -> 3.88Improved

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