AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Knowledge-Adaptation Priors

Mohammad Emtiyaz Khan, Siddharth Swaroop

NeurIPS 2021 · Architectures and efficiency › RNNs and normalization · approach: Neural scaling laws · 0 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
Use K-priors instead of Replay with the same memoryK-priors · UCI Adult, USPS odd vs even, USPS neural networksclassification performanceImproved
Use K-priors instead of full-batch retraining with limited memoryK-priors · UCI Adult and USPS odd vs even adaptation tasksclassification performanceNo clear effect
Use K-priors instead of full-batch retraining with limited memoryK-priors · CIFAR-10 Add Dataclassification performanceHurt
Add a temperature to K-priors (ablation)K-priors · CIFAR-10 Add Dataclassification performanceImproved
Add a temperature to K-priors (ablation)K-priors · CIFAR-10 Change Architectureclassification performanceImproved
Add the weight-space term centered at the base model (ablation)K-priors · USPS logistic regression adaptation tasksclassification performanceImproved
Replace the centered weight term with an uncentered weight penalty (ablation)K-priors · USPS logistic regression adaptation tasksclassification performanceHurt
Randomly initialize parameters instead of initializing at the previous parameters (ablation)K-priors · USPS odd vs even neural networks: Add Data, Remove Data, Change Regularizerclassification performanceNo clear effect
Choose Replay memory randomly instead of by highest h'(base prediction) (ablation)Replay · UCI Adult Add Dataclassification performanceNo clear effect
Use weight-priors instead of K-priors (ablation)Add Data adaptation · USPS odd vs even, logistic regression and neural networksclassification performanceHurt
Use weight-priors instead of K-priors (ablation)Add Data adaptation · UCI Adult, MNIST, and CIFAR-10classification performanceNo 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