AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Biological learning in key-value memory networks

Danil Tyulmankov, Ching Fang, Annapurna Vadaparty, Guangyu Robert Yang

NeurIPS 2021 · Architectures and efficiency › RNNs and normalization · approach: Hebbian and predictive coding · 3 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
random instead of sequential local third factors (ablation)key-value memory plasticity rule · Autoassociative recallcapacity: 1.0N -> 0.16NHurt
key-value memory with sequential third factors instead of classical Hopfield networkautoassociative memory · Autoassociative recallcapacity: 0.14N -> 1.0NImproved
random third-factor probability scales with network size (p=4/N) rather than fixed p=0.1 (ablation)random local third factor · Autoassociative recallcapacityImproved
replace local-third-factor decay of hidden-to-output synapses with passive decay (meta-learned) (ablation)meta-learned key-value memory · Autoassociative recallaccuracyNo clear effect
key-value memory vs Hopfield network with decaycontinual recall · Continual autoassociative recallaccuracyImproved
correlated memories (0.6) instead of uncorrelatedkey-value memory plasticity rule · Autoassociative recallaccuracyNo clear effect
key-value memory vs BAM on sequence recallsequence recall · Sequence recallaccuracyImproved
random or trained third factors instead of sequential in copy-paste task (ablation)copy-paste task · Copy-pastetask performanceHurt

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