19 lines
573 B
Plaintext
19 lines
573 B
Plaintext
|
<frame title="Anomaly Detection">
|
||
|
|
<split>
|
||
|
|
<que>
|
||
|
|
<list>
|
||
|
|
<e>Anomalies are rare, so often only a few datapoints known (e.g. Machine Failure in an Aircraft)</e>
|
||
|
|
<e>In practice, anomalies might appear that are not known during testing</e>
|
||
|
|
<e>->So train the model only on normal samples</e>
|
||
|
|
<e>Unsupervised Machine Learning</e>
|
||
|
|
<l2st>
|
||
|
|
<e>What can we say without knowing anomalies?</e>
|
||
|
|
<e>''Understand you dataset''</e>
|
||
|
|
</l2st>
|
||
|
|
</list>
|
||
|
|
</que>
|
||
|
|
<que>
|
||
|
|
<i f="..//prep/03Anomaly_Detection/usup.pdf" wmode="True"></i>
|
||
|
|
</que>
|
||
|
|
</split>
|
||
|
|
</frame>
|