AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Neural Edit Operations for Biological Sequences

Satoshi Koide, Keisuke Kawano, Takuro Kutsuna

NeurIPS 2018 · Architectures and efficiency › CNN design · approach: Biologically inspired CNN explanation · 14 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
replace convolution inner product with differentiable Needleman-Wunsch score (EINN), gap cost 2.5 (ablation)Tiny-CNN · CB513 (2% train data)accuracy (%): 42.0 -> 43.0Improved
replace convolutions in first ConvBlock with EINN (ablation)2-block CNN with augmentation · CB513accuracy (%): 69.7 -> 69.8Improved
set EINN gap cost large (g>10), prohibiting insertion/deletion (ablation)Tiny-EINN · CB513 (2% train data)accuracy (%): 43.0 -> 42.0Hurt
increase depth from 2 to 12 blocks (ablation)CNN with concatenation · CB513accuracy (%): 69.8 -> 71.5Improved
increase depth from 12 to 16 blocks (ablation)CNN with concatenation · CB513accuracy (%): 71.5 -> 71.3No clear effect
use modified ConvBlock with concatenation (ablation)12-block CNN · CB513accuracy (%): 71.5 -> 71.5No clear effect
use residual (additive skip) blocks instead of concatenation (ablation)deep CNN · CB513accuracy (%): 71.5 -> 71.0Hurt
random amino acid replacement data augmentation (15% of residues) (ablation)deep CNN · CB513accuracy (%): up to 0.8-pointsImproved
reduce training data to 1% (EINN vs CNN gain) (ablation)Tiny-EINN · CB513accuracy gain over CNN: 1.4% at 1%, 1.0% at 2%, 0.6% at 5%Improved
add pooling layers (ablation)deep CNN · CB513accuracy (%)No 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