Edited, memorised or added to reading queue

on 02-Oct-2025 (Thu)

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

Flashcard 7761217326348

Tags
#ML-engineering #ML_in_Action #learning #machine #software-engineering
Question
Perhaps the most confusing and complex part of ML project work for newer teams is in how to build a [...] deployment strategy.
Answer
cost-effective

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
Perhaps the most confusing and complex part of ML project work for newer teams is in how to build a cost-effective deployment strategy.

Original toplevel document (pdf)

cannot see any pdfs







Flashcard 7761219161356

Tags
#deep-learning #keras #lstm #python #sequence
Question

Input must be three-dimensional, comprised of samples, time steps, and features in that order.

Samples. These are the [...] in your data. One sample may be one sequence.

Answer
rows

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
Input must be three-dimensional, comprised of samples, time steps, and features in that order. Samples. These are the rows in your data. One sample may be one sequence.

Original toplevel document (pdf)

cannot see any pdfs







Flashcard 7761221520652

Tags
#recurrent-neural-networks #rnn
Question
To make the predicted transaction sequences robust against sampling noise, we repeat this process for each customer several times and take the mean expected number of transactions in [...] as our final result.
Answer
a given time step

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
pan> To make the predicted transaction sequences robust against sampling noise, we repeat this process for each customer several times and take the mean expected number of transactions in a given time step as our final result. <span>

Original toplevel document (pdf)

cannot see any pdfs