Edited, memorised or added to reading queue

on 30-Jan-2023 (Mon)

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

Flashcard 7560677690636

Tags
#deep-learning #keras #lstm #python #sequence
Question
Deep learning is built around a hypothesis that a deep, hierarchical model can be [...] more efficient at representing some functions than a shallow one
Answer
exponentially

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
Deep learning is built around a hypothesis that a deep, hierarchical model can be exponentially more efficient at representing some functions than a shallow one

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7560679525644

Tags
#deep-learning #keras #lstm #python #sequence
Question
[...] is a rescaling of the data from the original range so that all values are within the range of 0 and 1.
Answer
Normalization

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
Normalization is a rescaling of the data from the original range so that all values are within the range of 0 and 1.

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7560683195660

Tags
#causality #statistics
Question
[...] is a combination of consistency and no interference (and also deterministic potential outcomes)
Answer
SUTVA

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
SUTVA is a combination of consistency and no interference (and also deterministic potential outcomes)

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7560685292812

Tags
#feature-engineering #lstm #recurrent-neural-networks #rnn
Question
While an RNN can carry forward useful information from one timestep to the next, however, it is much less effective at capturing [...]-term dependencies (Bengio, Simard, & Frasconi, 1994; Pascanu, Mikolov, & Bengio, 2013). This limitation turns out to be a crucial problem in marketing analytics.
Answer
long

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
While an RNN can carry forward useful information from one timestep to the next, however, it is much less effective at capturing long-term dependencies (Bengio, Simard, & Frasconi, 1994; Pascanu, Mikolov, & Bengio, 2013). This limitation turns out to be a crucial problem in marketing analytics.

Original toplevel document (pdf)

cannot see any pdfs