AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Teacher Guided Architecture Search

Pouya Bashivan, Mark Tensen, James J. DiCarlo

ICCV 2019 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS · 24 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
add teacher RDM similarity (TG) to premature performance score (ablation)P-guided search · CIFAR-100 architecture search (RL, 10-layer space, 2 epochs/sample)best C100 error (%): 41.0 -> 38.3Improved
add teacher RDM similarity (TG) to premature performance score (ablation)P-guided search · CIFAR-100 architecture search (RL, 10-layer space, 20 epochs/sample)best C100 error (%): 40.5 -> 39.2Improved
add teacher RDM similarity (TG) to premature performance score (ablation)P-guided search · CIFAR-100 architecture search (RL, 20-layer space, 2 epochs/sample)best C100 error (%): 37.5 -> 33.2Improved
add teacher RDM similarity (TG) to premature performance score (ablation)P-guided search · CIFAR-100 architecture search (RL, 20-layer space, 20 epochs/sample)best C100 error (%): 32.7 -> 32.2Improved
add teacher RDM similarity (TG) to premature performance score (ablation)P-guided search · CIFAR-100 architecture search (TPE, 10-layer space, 2 epochs/sample)best C100 error (%): 42.5 -> 37.6Improved
add teacher RDM similarity (TG) to premature performance score (ablation)P-guided search · CIFAR-100 architecture search (TPE, 20-layer space, 2 epochs/sample)best C100 error (%): 37.0 -> 33.0Improved
use P+TG at 2 epochs/sample instead of P at 20 epochs/sample (ablation)P-guided search · CIFAR-100 architecture search (RL, 10-layer space)best C100 error (%): 40.5 -> 38.3Improved
increase TG weight alpha (ablation)P+TG score · predicting mature performancecorrelation with mature performanceMixed
use NASNet instead of ResNet as the teacher network (ablation)TG-SAGE · predicting mature performancecorrelation with mature performanceImproved
use macaque neural RDMs as teacher with P+TG instead of P alone (ablation)P-guided search · ImageNet top-1 errortop-1 error (%): 34.4 -> 32.54Improved
replace 7x1/1x7 convolutions with 7x7 separable convolutions (ablation)SAGENet · CIFAR-100 test errorerror (%): 17.42 -> 17.51No clear effect
replace 7x1/1x7 convolutions with 7x7 separable convolutions (ablation)SAGENet · CIFAR-10 test errorerror (%): 3.66 -> 3.88Hurt

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