AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Kernel similarity matching with Hebbian networks

Kyle Luther, Sebastian Seung

NeurIPS 2022 · Learning theory and algorithms › Kernels and regression theory · approach: RKHS kernel methods · 1 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
learn nonlinear features directly with Hebbian updateskernel similarity matching on Half Moons · Half Moons dataset, low output dimensionalitynormalized approximation errorImproved
use learned features as Nyström landmarks instead of the learned network responseskernel similarity matching · Half Moons datasetnormalized approximation errorImproved
increase output dimensionality (ablation)Hebbian kernel similarity matching · Half Moons datasetnormalized approximation errorHurt
increase output dimensionality (ablation)Hebbian kernel similarity matching · MNIST, α=1 and α=3normalized approximation errorHurt
use kernel PCA instead of the proposed learned featureskernel approximation on MNIST · MNIST, α=3normalized approximation errorImproved
use Nyström landmarks from KMeans or learned features rather than sampled landmarkskernel approximation on MNIST · MNIST, α=3normalized approximation errorImproved
use the linear kernel (α=1) rather than nonlinear power-cosine kernels (ablation)Hebbian kernel similarity matching · MNISTlinear classifier test accuracyMixed
use nonlinear power-cosine kernels (α=2, 3, or 4) rather than the linear kernel (ablation)Hebbian kernel similarity matching · MNISTlinear classifier test accuracyImproved
increase kernel exponent from α=1 toward α=2, 3, or 4 (ablation)Hebbian kernel similarity matching · MNISTresponse sparsityImproved
use a higher-dimensional random Fourier representationGaussian-kernel approximation · Half Moons datasetnormalized approximation errorImproved
use a large ratio of feature and regulatory learning rates to lateral learning rate (ablation)Hebbian kernel similarity matching · training convergenceconvergenceHurt

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