sampling based on divergence
Project description
AutoRA Divergence Experimentalist
The divergence experimentalist identifies experimental conditions $\vec{x}' \in X'$ with respect the distance between existing experimental data $\vec{x}, $\vec{y} and data predicted by a model $\vec{x_pool}, $\vec{y_pred}:
$$ \underset{\vec{x}'}{\arg\max}~sum(d((\vec{x}, \vec{y}), (\vec{x_pool}, \vec{y_pred})) $$
The aim of this experimentalist is to combine novelty and uncertainty by using a distance that combines both: The distance between existing conditions to new conditions and the distance of existing observations to predictions.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Close
Hashes for autora_experimentalist_divergence-0.0.1.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8b7a61df0d1aa57731c0fedf27b54efb35fde4d27812441abee24aa1cb21e6de |
|
MD5 | 01417cbccc6346598506ec7a55a5a595 |
|
BLAKE2b-256 | ee1990761d732e21b2e0b0a03f4a27e97fc3a3fbc8e50e0151e7b00f49a15d74 |
Close
Hashes for autora_experimentalist_divergence-0.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 1adc78c2741a752bbfd885c3e47c685010248e22ad0efb4ea791fcc2dd09033d |
|
MD5 | 50ab3858a48a689502a48770fc952824 |
|
BLAKE2b-256 | 51673b8703bc92e2614f5bd037cd39961bdc1b3a20a158bbef94f0a7ba60e756 |