AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

The Tree Ensemble Layer: Differentiability meets Conditional Computation

Hussein Hazimeh, Natalia Ponomareva, Petros Mol, Zhenyu Tan, Rahul Mazumder

ICML 2020 · Architectures and efficiency › RNNs and normalization · approach: Neural-symbolic reasoning · 16 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 final dense layers with a dense layer followed by TELCNN · CIFAR-10 testloss: 1.673 ± 0.170 -> 1.202 ± 0.011Improved
Replace final dense layers with a dense layer followed by TELCNN · CIFAR-10 testnumber of parameters: 7,548,362 -> 926,465Improved
Replace final dense layers with a dense layer followed by TELCNN · MNIST testloss: 0.03620 ± 0.00121 -> 0.03379 ± 0.00093Improved
Replace final dense layers with a dense layer followed by TELCNN · Fashion MNIST testloss: 0.6930 ± 0.0291 -> 0.3247 ± 0.0045Improved
Replace final dense layers with a dense layer followed by TELCNN · Fashion MNIST testaccuracy: 0.9299 ± 0.0012 -> 0.9297 ± 0.0012No clear effect
Use smooth-step routing instead of logistic routing (ablation)TEL · PMLB datasetsAUC: 7 wins vs. 7 winsMixed
Use smooth-step routing instead of logistic routing (ablation)TEL · PMLB datasets, depth 10training speedup: over $10$xImproved
Jointly optimize an ensemble with TEL rather than use stage-wise GBDTtree ensemble · pima, comparable AUCnumber of trees: more than 100 -> 5Improved
Use TEL instead of GBDTstandalone learner · PMLB datasetsAUC wins: TEL: 12; GBDT: 14Mixed

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