Edited, memorised or added to reading queue

on 13-Jan-2026 (Tue)

Do you want BuboFlash to help you learning these things? Click here to log in or create user.

Annotation 7786847669516

3.1.3 Practical Considerations When Scaling
#deep-learning #keras #lstm #python #sequence
Scale if in Doubt
You probably do need to rescale your input and output variables. If in doubt, at least normalize your data.
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
ationary. It would not be appropriate to scale the series after it has been transformed into a supervised learning problem as each column would be handled differently, which would be incorrect. <span>Scale if in Doubt You probably do need to rescale your input and output variables. If in doubt, at least normalize your data. <span>

Original toplevel document (pdf)

cannot see any pdfs



Flashcard 7786850553100

Tags
#feature-engineering #lstm #recurrent-neural-networks #rnn
Question
Customers tend to [...] past events, at least partially. Hence, the effects of marketing actions tend to carry-over into numerous subsequent periods
Answer
remember

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
Customers tend to remember past events, at least partially. Hence, the effects of marketing actions tend to carry-over into numerous subsequent periods

Original toplevel document (pdf)

cannot see any pdfs