AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Binarized Neural Architecture Search

AAAI 2020 · Architectures and efficiency › Neural architecture search · approach: Efficient NAS search strategies · 25 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 BNAS full-precision search instead of PC-DARTSfull-precision architecture search · CIFAR-10search cost (GPU days): 0.15 -> 0.08Helped
use BNAS full-precision search instead of PC-DARTSfull-precision architecture search · CIFAR-10test error (%): 2.78 -> 2.84Hurt
increase initial channels to 44 (ablation)BNAS (XNOR) · CIFAR-10test error (%): 5.71 -> 4.88Helped
increase initial channels to 48 (ablation)BNAS (PCNN) · CIFAR-10test error (%): 3.94 -> 3.47Helped
use BNAS with PCNN instead of PC-DARTS with PCNNbinarized architecture search · CIFAR-10test accuracy (%): 95.12% -> 96.06%Helped
use BNAS with PCNN instead of PC-DARTS with PCNNbinarized architecture search · CIFAR-10search cost (GPU days): 0.18 -> 0.09375Helped
use BNAS (PCNN) instead of PC-DARTSarchitecture search · ImageNetsearch cost (GPU days): 3.8 -> 2.6Helped
use BNAS (PCNN) instead of PC-DARTSarchitecture search · ImageNetTop1 accuracy (%): 75.8 -> 71.3Hurt

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