BIRDNet mines Boolean implications from data to wire a sparse interpretable neural network whose units directly correspond to mined rules, matching dense MLP AUROC within 0.02 while using up to 96x fewer active parameters.
gene expression cancer RNA-Seq
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
MEDAL distills manifold embeddings into autoencoders to enable out-of-sample extension and held-out validation of dimension reduction methods.
citing papers explorer
-
BIRDNet: Mining and Encoding Boolean Implication Knowledge Graphs as Interpretable Deep Neural Networks
BIRDNet mines Boolean implications from data to wire a sparse interpretable neural network whose units directly correspond to mined rules, matching dense MLP AUROC within 0.02 while using up to 96x fewer active parameters.
-
MEDAL: Manifold Embedding Distillation via Autoencoder Learning
MEDAL distills manifold embeddings into autoencoders to enable out-of-sample extension and held-out validation of dimension reduction methods.