AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Dynamic Optimization of Neural Network Structures Using Probabilistic Modeling

Shinichi Shirakawa, Yasushi Iwata, Youhei Akimoto

AAAI 2018 · Architectures and efficiency › Neural architecture search · approach: Latency-aware architecture search · 30 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 the same mini-batch to compare sampled layer structures rather than different mini-batches (ablation)AdaptiveLayer · MNISTtest error (%): 15.69 (29.9) -> 2.200 (0.125)Improved
Initialize layer-skip probabilities at 0.5 instead of 0.969 (ablation)AdaptiveLayer (b) · MNISTtest error (%): 35.26 (41.6) -> 15.69 (29.9)Improved
Optimize layer-skip probabilities instead of keeping them fixed at 0.5 (ablation)StochasticLayer · MNISTtest error (%): 4.704 (0.752) -> 2.200 (0.125)Improved
Use deterministic rather than stochastic prediction (ablation)AdaptiveLayer (a) · MNISTtest error (%): 2.200 (0.125) -> 2.218 (0.135)No clear effect
Use deterministic rather than stochastic prediction (ablation)AdaptiveConnection · CIFAR-100test error (%): 25.461 (0.408) -> 25.315 (0.409)No clear effect
Optimize activation probabilities instead of keeping them fixed at 0.5 (ablation)AdaptiveActivation · MNISTtest error (%): 1.452 (0.025) -> 1.407 (0.036)Improved
Learn a mixture of ReLU and tanh activations instead of using ReLU for every unit (ablation)AdaptiveActivation · MNISTtest error (%): 1.609 (0.044) -> 1.414 (0.054)Improved
Learn a mixture of ReLU and tanh activations instead of using tanh for every unit (ablation)AdaptiveActivation · MNISTtest error (%): 1.592 (0.069) -> 1.414 (0.054)Improved
Use deterministic rather than stochastic prediction (ablation)AdaptiveActivation · MNISTtest error (%): 1.414 (0.054) -> 1.407 (0.036)No clear effect
Optimize network structures jointly during training rather than search them with Bayesian optimization at budget 10AdaptiveNet · MNISTtime (hour): 9.59 -> 1.01Improved
Optimize network structures jointly during training rather than use Bayesian optimization at budget 20AdaptiveNet · MNISTtest error (%): 1.490 -> 1.645 (0.072)Hurt
Select DenseNet connections instead of keeping all connections (ablation)AdaptiveConnection · CIFAR-10test error (%): 5.050 (0.147) -> 5.427 (0.167)Hurt

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