Edited, memorised or added to reading queue

on 27-Mar-2025 (Thu)

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

Annotation 7692394827020

#causality #statistics
In this manipulated graph, there cannot be any backdoor paths because no edges are going into the backdoor of 𝑇 . Therefore, all of the association that flows from 𝑇 to π‘Œ in the manipulated graph is purely causal
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
if we take the graph from Figure 4.5 and intervene on 𝑇 , then we get the manipulated graph in Figure 4.6. In this manipulated graph, there cannot be any backdoor paths because no edges are going into the backdoor of 𝑇 . Therefore, all of the association that flows from 𝑇 to π‘Œ in the manipulated graph is purely causal

Original toplevel document (pdf)

cannot see any pdfs



Annotation 7692396662028

#deep-learning #keras #lstm #python #sequence
Long Short-Term Memory (LSTM) is an RNN architecture specifically designed to address the vanishing gradient problem
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
output, either decays or blows up exponentially as it cycles around the network’s recurrent connections. This shortcoming ... referred to in the literature as the vanishing gradient problem ... <span>Long Short-Term Memory (LSTM) is an RNN architecture specifically designed to address the vanishing gradient problem. β€” A Novel Connectionist System for Unconstrained Handwriting Recognition, 2009 <span>

Original toplevel document (pdf)

cannot see any pdfs



Flashcard 7692399021324

Tags
#RNN #ariadne #behaviour #consumer #deep-learning #priority #recurrent-neural-networks #retail #simulation #synthetic-data
Question
For event-stream RNNs, history inputs xt ∈ R20 consist of a one-hot encoding of the action type and the time difference. For session-stream RNNs, history inputs st ∈ R23 represent sessions with binary indicators which action types occurred, the time difference to the previous session and the characteristics described in Sec. 3.2. Time differences and, in case of session-stream RNNs, the total session event counts are [...].
Answer
logarithmized

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
pes occurred, the time difference to the previous session and the characteristics described in Sec. 3.2. Time differences and, in case of session-stream RNNs, the total session event counts are <span>logarithmized. <span>

Original toplevel document (pdf)

cannot see any pdfs