AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Using Conceptors to Manage Neural Long-Term Memories for Temporal Patterns

Herbert Jaeger

JMLR 2017 · Architectures and efficiency › RNNs and normalization · approach: LSTM design and memory · 53 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
auto-adapt the conceptor after cueing instead of using the preliminary cue conceptor (ablation)Autoconceptor recall · 5-periodic and mix-of-sines patternsNRMSEImproved
add state noise during autonomous auto-adaptation (ablation)Autoconceptor recall, mix of sines · Mix of 2 sines (10 patterns)adaptation steps needed: 1,000,000 steps without noise vs 10,000 with noiseImproved
remove cue and state noise (ablation)Autoconceptor recall, 5-periodic patterns · 5-periodic patternsNRMSE: 0.070 -> 0.0037Improved
use autoconceptors instead of stored alloconceptorsConceptor recall, mix of sines · Mix of 2 sines (10 patterns)NRMSE: 0.087 -> 0.11Hurt
use autoconceptors instead of stored alloconceptors under noiseConceptor recall, 5-periodic patterns · 5-periodic patternsNRMSE: .0033 -> 0.070Hurt
adapt conceptor with loss on filtered state z instead of reservoir output r (ablation)Autoconceptor adaptation · 5-periodic patternsnoise robustness and singular value profileImproved
load more patterns from a parametric family (ablation)Autoconceptor recall of novel patterns · Mix of 2 sines family, N=100log10 NRMSE of novel patterns: within 20% of loaded-pattern accuracy at about 5 patternsImproved
load more patterns into the reservoir (ablation)Autoconceptor recall of loaded patterns · Mix of 2 sines family, N=100NRMSE of loaded patternsHurt
set aperture far from the optimal value (ablation)Alloconceptor recall of Lorenz attractor · Lorenz attractorvisual matchNo clear effect

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