← Back to context

Comment by heavyset_go

3 days ago

It's very easy to train a model to identify anomalies like that.

While it's definitely possible to train a model for that, 'very easy' is nonsense.

Unless you've got some superintelligence hidden somewhere, you'd choose a neural net. To train, you need a large supply of LABELED data. Seems like a challenge to build that dataset; after all, we have no scalable method for classifying as of yet.