AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Adaptive Neural Trees

Ryutaro Tanno, Kai Arulkumaran, Daniel Alexander, Antonio Criminisi, Aditya Nori

ICML 2019 · Architectures and efficiency › RNNs and normalization · approach: Mechanistic circuit interpretability · 23 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
Combine learned feature transformations with hierarchical router-based data partitioning (ablation)Adaptive Neural Trees · SARCOS, MNIST, CIFAR-10prediction error: SARCOS: 1.38 vs 2.51 and 2.12; MNIST-A: 0.64 vs 0.74 and 3.18; CIFAR10-A: 8.31 vs 9.29 and 39.29Improved
Add router-based hierarchical partitioning (ablation)Adaptive Neural Trees · SARCOS, MNIST-A/B/C, CIFAR10-A/B/Cprediction error: 1.38 -> 2.51; 0.64 -> 0.74; 0.72 -> 0.80; 1.62 -> 3.71; 8.31 -> 9.29; 9.15 -> 11.08; 9.31 -> 11.61Improved
Add learned transformer modules for feature learning (ablation)Adaptive Neural Trees · SARCOS, MNIST-A/B/C, CIFAR10-A/B/Cprediction error: 1.38 -> 2.12; 0.64 -> 3.18; 0.72 -> 4.63; 1.62 -> 5.70; 8.31 -> 39.29; 9.15 -> 43.09; 9.31 -> 48.59Improved
Use single-path instead of multi-path inferenceAdaptive Neural Trees · SARCOS, MNIST, CIFAR-10prediction error: 1.384 -> 1.542; 0.64 -> 0.69; 8.31 -> 8.32No clear effect
Use ANT-MNIST-B with smaller convolution kernels than ANT-MNIST-AANT-MNIST-A · MNISTclassification error: 0.64 -> 0.72Hurt
Match the root-to-path CNN's parameter count to ANT-MNIST-CANT-MNIST-C · MNISTclassification error: 1.68 -> 3.55Hurt
Initialize routers and transformers from a pre-trained single-path CNNANT-MNIST-A · CIFAR-10classification error: 8.31 -> 6.72Improved
Globally refine all modules after architecture growthAdaptive Neural Trees · CIFAR-10test accuracyImproved
Set growth-phase patience to 1 (ablation)ANT-CIFAR10-C · CIFAR-10validation accuracy: 80%Hurt
Set growth-phase patience to 15 (ablation)ANT-CIFAR10-C · CIFAR-10validation accuracy: 87%Hurt
Set growth-phase patience to 5 (ablation)ANT-CIFAR10-C · CIFAR-10validation accuracy: 91%Improved
Ensemble 8 ANT modelsAdaptive Neural Trees · MNIST, CIFAR-10, SARCOSprediction error: MNIST 0.64 -> 0.29; CIFAR-10 8.31 -> 7.76; SARCOS 1.384 -> 1.226Improved

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