Edited, memorised or added to reading queue

on 16-Oct-2025 (Thu)

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

Flashcard 7763354848524

Tags
#feature-engineering #lstm #recurrent-neural-networks #rnn
Question

The learning mechanism of the recurrent neural network thus involves:

...

(2) the backpropagation step where the [...] of the parameters with respect to the loss is calculated; and finally,

...

Answer
gradient

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
The learning mechanism of the recurrent neural network thus involves: ... (2) the backpropagation step where the gradient of the parameters with respect to the loss is calculated; and finally, ...

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7763356683532

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

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






Flashcard 7763358518540

Tags
#has-images #recurrent-neural-networks #rnn
[unknown IMAGE 7100426751244]
Question
Conversely, how about the next ten individuals 1011–1020, who have all made a number of transactions historically, but recently have been on an unusually long [...]?
Answer
hiatus

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
Conversely, how about the next ten individuals 1011–1020, who have all made a number of transactions historically, but recently have been on an unusually long hiatus?

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7763360615692

Tags
#recurrent-neural-networks #rnn
Question
We demonstrate how firms operating in non-contractual business settings can benefit from the [...] feature extraction capabilities of deep learning models for predictive customer base analysis
Answer
automatic

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
We demonstrate how firms operating in non-contractual business settings can benefit from the automatic feature extraction capabilities of deep learning models for predictive customer base analysis

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7763362974988

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

3.1.3 Practical Considerations When Scaling

There are some practical considerations when scaling sequence data.

Save Coefficients
You will need to scale new data in the future in exactly the same way as the data used to train your model. Save the coefficients used to file and load them later when you need to scale new data when [...].

Answer
making predictions

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
ll need to scale new data in the future in exactly the same way as the data used to train your model. Save the coefficients used to file and load them later when you need to scale new data when <span>making predictions. <span>

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7763364809996

Tags
#deep-learning #has-images #keras #lstm #python #sequence
[unknown IMAGE 7104054824204]
Question
You can specify the [...] argument that expects a tuple containing the number of time steps and the number of features
Answer
input shape

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
You can specify the input shape argument that expects a tuple containing the number of time steps and the number of features

Original toplevel document (pdf)

cannot see any pdfs