AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Neural Architecture Search for Spiking Neural Networks

Youngeun Kim, Yuhang Li, Hyoungseob Park, Yeshwanth Venkatesha, Priyadarshini Panda

ECCV 2022 · Architectures and efficiency › Neural architecture search · approach: Efficient NAS search strategies · 124 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 backward (temporal feedback) connections to searched cell (ablation)SNASNet · CIFAR10 (T=5)accuracy (%): 93.12 -> 93.73Improved
add backward connections to searched cell (ablation)SNASNet · CIFAR100 (T=5)accuracy (%): 70.06 -> 73.04Improved
add backward connections to searched cell (ablation)SNASNet · TinyImageNet (T=5)accuracy (%): 52.81 -> 54.60Improved
use Sparsity-Aware Hamming Distance instead of plain Hamming distance (ablation)SNASNet-Fw · CIFAR100accuracy (%): 64.16 -> 70.06Improved
use Sparsity-Aware Hamming Distance instead of plain Hamming distance (ablation)SNASNet-Bw · CIFAR100accuracy (%): 66.80 -> 73.04Improved
increase timesteps from 5 to 20 (ablation)SNASNet-Fw · CIFAR100accuracy (%): 70.06 -> 70.52Improved
increase timesteps from 5 to 20 (ablation)SNASNet-Bw · CIFAR100accuracy (%): 73.04 -> 74.24Improved
transfer architecture searched on CIFAR10 to TinyImageNet (backward) (ablation)SNASNet-Bw · TinyImageNetaccuracy (%): -0.80 vs original searchHurt
transfer backward architecture searched on CIFAR100 to TinyImageNet (ablation)SNASNet-Bw · TinyImageNetaccuracy (%): +0.59 vs original searchImproved
transfer forward architectures searched on another dataset (ablation)SNASNet-Fw · CIFAR10, CIFAR100, TinyImageNetaccuracy (%): -0.56 to +0.11No clear effect
use more than 2 backward skip connections (ablation)SNASNet-Bw · CIFAR100accuracy (%)Hurt
use average pooling in cells (ablation)SNASNet-Fw · CIFAR100accuracy (%)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