AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Weight Agnostic Neural Networks

Adam Gaier, David Ha

NeurIPS 2019 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 77 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
Search architectures with a single shared weight instead of using a fixed topologyCartPoleSwingUp · CartPoleSwingUpcumulative reward with random shared weight: 7 ± 2 -> 515 ± 58Improved
Search architectures with a single shared weight instead of using a fixed topologyBipedalWalker-v2 · BipedalWalker-v2cumulative reward with random shared weight: -107 ± 12 -> 51 ± 108Improved
Search architectures with a single shared weight instead of using a fixed topologyCarRacing-v0 · CarRacing-v0cumulative reward with random shared weight: -85 ± 27 -> 375 ± 177Improved
Tune the shared weight after WANN architecture searchWANN · CartPoleSwingUpcumulative reward: 515 ± 58 -> 723 ± 16Improved
Tune the shared weight after WANN architecture searchWANN · BipedalWalker-v2cumulative reward: 51 ± 108 -> 261 ± 58Improved
Tune the shared weight after WANN architecture searchWANN · CarRacing-v0cumulative reward: 375 ± 177 -> 608 ± 161Improved
Use a fixed single weight value rather than training across a range of values (ablation)WANN search · continuous control tasksrobust task performanceHurt
Use independently random weights for each connection rather than one shared weight (ablation)WANN search · continuous control taskstask performanceHurt
Add Gaussian noise to the shared weight values (ablation)WANN · CartPoleSwingUpcumulative rewardNo clear effect
Add very high levels of Gaussian noise to shared weight values (ablation)WANN · CartPoleSwingUpcumulative rewardHurt
Fine-tune WANN weights with backpropagation rather than black-box optimization (ablation)MNIST WANN · MNISTaccuracyHurt

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