AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Stochastic Deep Networks with Linear Competing Units for Model-Agnostic Meta-Learning

Konstantinos Kalais, Sotirios Chatzis

ICML 2022 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 2 citations (OpenAlex)

Read the paper

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
Use stochastic instead of deterministic LWTA competition (ablation)StochLWTA-ML · Omniglot 20-way 1-shotaccuracy: 96.95 -> 97.79Improved
Use stochastic instead of deterministic LWTA competition (ablation)StochLWTA-ML · Omniglot 20-way 5-shotaccuracy: 98.63 -> 98.97Improved
Use stochastic instead of deterministic LWTA competition (ablation)StochLWTA-ML · Mini-Imagenet 5-way 1-shotaccuracy: 53.12 -> 54.11Improved
Use stochastic instead of deterministic LWTA competition (ablation)StochLWTA-ML · Mini-Imagenet 5-way 5-shotaccuracy: 64.93 -> 66.70Improved
Increase competing units per block from J=2 to J=4 (ablation)StochLWTA-ML · Omniglot 20-way 1-shotaccuracy: 97.79 -> 96.33Hurt
Increase competing units per block from J=2 to J=8 (ablation)StochLWTA-ML · Omniglot 20-way 1-shotaccuracy: 97.79 -> 95.38Hurt
Replace Gaussian weights with point-estimate weights (ablation)StochLWTA-ML · Omniglot 20-way 1-shotaccuracy: 97.68 -> 97.79Hurt
Replace Gaussian weights with point-estimate weights (ablation)StochLWTA-ML · Omniglot 20-way 5-shotaccuracy: 98.85 -> 98.97Hurt
Use a stochastic LWTA network with 4 convolutional layers instead of the compact architecture (ablation)StochLWTA-ML · Omniglot 20-way 1-shotaccuracy: 97.79 -> 96.50Hurt
Use stochastic LWTA and Bayesian weights instead of deterministic ReLU networks with point-estimate weights (ablation)Meta-learning classifiers · Omniglot 20-way 1-shotaccuracy: 2.2% and 3.5% reductionImproved

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