September 2019 Archiv

Wer Wo Wann.

Für mehr Meta-Informationen in der Alltagssprache!

myself on twitter, 2010-05-18

But wait until they find our flow-charts.

Quick, in high school were you ever told not to date your old girlfriend’s current boyfriend’s old girlfriend? Or your old boyfriend’s current girlfriend’s old boyfriend? Probably not. But I bet you never did, either.

Kieran Healy: Love is a Battlefield Spanning-Tree Network with no 4-Cycles

Let the devil take tomorrow.

All I'm taking is your time.

Gladys Knight & The Pips: Help to make me through the night

IThink.

De uiteindelijke betekenis van de informatietechnologie ligt niet in de producten die zij levert maar in de denkwijze die zij ons leert.

Peter J. de Bruin: Stelling 4 behorend bij het proefschrift Inductive Types in Constructive Languages

Wronderstanding.

When patterns in the dataset are aligned with the goal of the task at hand, a strong learner being able to recognize, remember, and generalize these patterns is desirable. But if the patterns are not what we're actually interested in, then they become cues and shortcuts that allow the model to perform well without understanding the task.
To prevent the Clever Hans effect, we hence need to aim for datasets without spurious patterns, and we need to assume that a well-performing model didn't learn anything useful until proven otherwise.

Benjamin Heinzerling: NLP's Clever Hans Moment has Arrived