Research
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.

169,042 papers · 148 categories

Trend · papers per month

count% of corpus
0.3%0.5%0.8%0.1% · Jan 201919922001200920172026
2 results for “z-normalizing”
Insights into LSTM Fully Convolutional Networks for Time Series Classificationcs.LG

LSTM-FCN and ALSTM-FCN improve time series classification performance.

problem Improving time series classification performance.
method Ablation tests on LSTM-FCN and ALSTM-FCN, comparing z-normalizing techniques, dimension shuffle impact, and GRU replacement.
result LSTM and FCN blocks perform better together, and z-normalizing the whole dataset is more effective.
LSTM-FCNALSTM-FCNtime series classificationablation testsz-normalizing
2019-02-27abs ↗pdf ↗