Edited, memorised or added to reading queue

on 05-Oct-2025 (Sun)

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

Flashcard 7750266260748

Tags
#ML-engineering #ML_in_Action #learning #machine #software-engineering
Question
ML engineers need to know just enough [...] skills to be able to write modular code and implement unit tests. They don’t need to know about the intricacies of non-blocking asynchronous messaging brokering.
Answer
software development

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
ML engineers need to know just enough software development skills to be able to write modular code and implement unit tests. They don’t need to know about the intricacies of non-blocking asynchronous messaging brokering.

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7757351488780

Tags
#deep-learning #keras #lstm #python #sequence
Question
Long Short-Term Memory (LSTM) is an [...] architecture specifically designed to address the vanishing gradient problem
Answer
RNN

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
Long Short-Term Memory (LSTM) is an RNN architecture specifically designed to address the vanishing gradient problem

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7761662446860

Tags
#deep-learning #keras #lstm #python #sequence
Question
If your problem looks like a traditional autoregression type problem with the most relevant lag observations within a small window, then perhaps develop a baseline of performance with an MLP and [...] before considering an LSTM
Answer
sliding window

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
f your problem looks like a traditional autoregression type problem with the most relevant lag observations within a small window, then perhaps develop a baseline of performance with an MLP and <span>sliding window before considering an LSTM <span>

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7761664281868

Tags
#recurrent-neural-networks #rnn
Question
non-contractual business settings (i.e., when the time at which a customer becomes inactive is [...] by the firm)
Answer
unobserved

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
non-contractual business settings (i.e., when the time at which a customer becomes inactive is unobserved by the firm)

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7761665592588

Tags
#knative #okd #serverless
Question

Scaling based on [...]

command: kn service update qura-rest-api --concurrency-limit 1 --scale-window=10s

Answer
concurrency

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Skalowanie w Knative serving
Scaling based on concurrency command: kn service update qura-rest-api --concurrency-limit 1 --scale-window=10s