AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Dense Associative Memory for Pattern Recognition

Dmitry Krotov, John J. Hopfield

NeurIPS 2016 · Architectures and efficiency › RNNs and normalization · approach: Representation geometry and collapse · 27 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
Increase energy power from n=2 to n=3Dense associative memory · MNISTtest error: 1.6%Improved
Increase energy power from n=2 to n=3Dense associative memory · MNISTepochs to cross 2% error: 179-312 -> 158-262Improved
Use energy power n=2 or n=3 instead of n≥5Dense associative memory with N=100 and K=2000 · Random binary memory retrievalperfect memory recovery: K=2000; K^max_no errors≈11 for n=2 and K^max_no errors≈360 for n=3Hurt
Use n=4 with K=2000Dense associative memory · Random binary memory retrieval, N=100overlap with closest memory: K^max_no errors≈7240Improved
Use higher rectified polynomial powers instead of ReLU (n=2)Dense associative memory / equivalent one-hidden-layer network · MNISTepochs to cross 2% error: 179-312 -> 158-262Improved
Use cross-entropy with softmax instead of the stated objective and output (ablation)Dense associative memory classifier · MNISTclassification performanceHurt
Increase the objective power m, emphasizing examples with largest target discrepancy (ablation)Dense associative memory classifier · MNIST, at least for large ngeneralizationImproved

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