On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “ChemNet”

Using Rule-Based Labels for Weak Supervised Learning: A ChemNet for Transferable Chemical Property Predictionstat.ML

ChemNet uses rule-based labels for weakly supervised learning to predict chemical properties.

problem Lack of labeled data in chemistry.

method Rule-based knowledge for training ChemNet, a deep neural network, on large unlabeled chemical databases.

result ChemNet outperforms DNN models trained with conventional supervised learning on smaller datasets.

ChemNet weakly supervised learning chemical property prediction transfer learning domain knowledge

2017-12-07abs ↗pdf ↗

Fréchet ChemNet Distance: A metric for generative models for molecules in drug discoverycs.LG

A new metric assesses generative models for molecules in drug design.

problem Difficulty in evaluating generative models for molecules.

method Fréchet ChemNet Distance (FCD) using a deep neural network trained to predict drug activities.

result FCD detects diversity and similarity of generated molecules to real ones.

drug design generative models molecular generation Fréchet ChemNet distance FID

2018-03-26abs ↗pdf ↗