Edited, memorised or added to reading queue

on 14-Jan-2026 (Wed)

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

Flashcard 7787184524556

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

3 common examples for managing state:

  • A prediction is made at the end of each sequence and sequences are independent. State should be reset after each sequence by setting the batch size to [...].
Answer
1

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> 3 common examples for managing state: A prediction is made at the end of each sequence and sequences are independent. State should be reset after each sequence by setting the batch size to <span>1. <span>

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7787186883852

Tags
#DAG #causal #edx
Question

What is the backdoor path criterion?

This is a graphical rule that tells us whether we can identify the causal effect of interest if we know the causal DAG.

And the rule is the following:

we can identify the causal effect of A and Y if we have [...] to block all backdoor paths between A and Y

Answer
sufficient data

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
phical rule that tells us whether we can identify the causal effect of interest if we know the causal DAG. And the rule is the following: we can identify the causal effect of A and Y if we have <span>sufficient data to block all backdoor paths between A and Y <span>

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7787188718860

Tags
#deep-learning #keras #lstm #python #sequence
Question
The LSTM [...] layer must be 3D
Answer
input

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 LSTM input layer must be 3D

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7787190553868

Tags
#causality #statistics
Question
The idea is that although the treatment and potential outcomes may be unconditionally [...] (due to confounding), within levels of 𝑋 , they are not associated
Answer
associated

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 idea is that although the treatment and potential outcomes may be unconditionally associated (due to confounding), within levels of 𝑋 , they are not associated

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7787192388876

Tags
#feature-engineering #lstm #recurrent-neural-networks #rnn
Question
The RNN has a multidimensional hidden state, which summarizes task-relevant information from the [...] and is updated at each timestep as well
Answer
entire history

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 RNN has a multidimensional hidden state, which summarizes task-relevant information from the entire history and is updated at each timestep as well

Original toplevel document (pdf)

cannot see any pdfs