Edited, memorised or added to reading queue

on 21-Jan-2026 (Wed)

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

Annotation 7674650561804

#RNN #ariadne #behaviour #consumer #deep-learning #priority #recurrent-neural-networks #retail #simulation #synthetic-data
A session is a well-defined visit of a consumer to a web-shop: a subsequence of events within the consumer’s history that lay no further apart than a predefined time difference
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
To achieve better explainability, in many e-commerce applications consumer behavior can be viewed on the level of sessions. A session is a well-defined visit of a consumer to a web- shop: a subsequence of events within the consumer’s history that lay no further apart than a predefined time difference.

Original toplevel document (pdf)

cannot see any pdfs



Flashcard 7789027921164

Tags
#ML-engineering #ML_in_Action #learning #machine #software-engineering
Question
ML engineers also need just enough [...] experience to know how to properly define, scope, and control a project to solve a problem, but they need not go through a PMP certification
Answer
project management

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 also need just enough project management experience to know how to properly define, scope, and control a project to solve a problem, but they need not go through a Project Management Professional (PMP) certification </s

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7789031591180

Tags
#deep-learning #keras #lstm #python #sequence
Question
Sequence generation involves generating a new output sequence that has the same general characteristics as other sequences in the corpus. For example: Input Sequence: [1, 3, 5], [7, 9, 11] Output Sequence: [3, [...]]
Answer
5 ,7

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
ion involves generating a new output sequence that has the same general characteristics as other sequences in the corpus. For example: Input Sequence: [1, 3, 5], [7, 9, 11] Output Sequence: [3, <span>5 ,7] <span>

Original toplevel document (pdf)

cannot see any pdfs






Annotation 7789033688332

#DAG #causal #inference
In this book, we stress the need to take the causal question seriously enough to articulate it, and to delineate the separate roles of data and assumptions for causal inference. Once these foundations are in place, causal inferences become necessarily less casual, which helps prevent confusion.
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
In this book, we stress the need to take the causal question seriously enough to articulate it, and to delineate the separate roles of data and assumptions for causal inference. Once these foundations are in place, causal inferences become necessarily less casual, which helps prevent confusion. The book describes various data analysis approaches to estimate the causal effect of interest under a particular set of assumptions when data are collected on each individual in a popula

Original toplevel document (pdf)

cannot see any pdfs



Flashcard 7789036571916

Tags
#causal #inference
Question

The G-methods family, as developed by James Robins and colleagues, specifically includes:

  1. Inverse probability weighting (IPW)
  2. [...]
  3. G-estimation of structural nested models
Answer
G-computation

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 G-methods family, as developed by James Robins and colleagues, specifically includes: Inverse probability weighting (IPW) G-computation G-estimation of structural nested models

Original toplevel document

Open it
The G-methods family, as developed by James Robins and colleagues, specifically includes: Inverse probability weighting (IPW) G-computation G-estimation of structural nested models Inverse probability matching (propensity score matching) is not technically a G-method. While it shares the fundamental goal of addressing confounding and selection bias, it employs a d






Flashcard 7789039193356

Tags
#RNN #ariadne #behaviour #consumer #deep-learning #priority #recurrent-neural-networks #retail #simulation #synthetic-data
Question
A session is a well-defined visit of a consumer to a web-shop: a subsequence of events within the consumer’s history that lay no further apart than a [...]
Answer
predefined time difference

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
A session is a well-defined visit of a consumer to a web-shop: a subsequence of events within the consumer’s history that lay no further apart than a predefined time difference

Original toplevel document (pdf)

cannot see any pdfs






Annotation 7789041290508

#ML-engineering #ML_in_Action #learning #machine #software-engineering
cost-effective deployment strategy. If it’s underpowered, the prediction quality doesn’t matter (since the infrastructure can’t properly serve the predictions). If it’s overpowered, you’re effectively burning money on unused infrastructure and complexity
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
Perhaps the most confusing and complex part of ML project work for newer teams is in how to build a cost-effective deployment strategy. If it’s underpowered, the prediction quality doesn’t matter (since the infrastructure can’t properly serve the predictions). If it’s overpowered, you’re effectively burning money on unused infrastructure and complexity

Original toplevel document (pdf)

cannot see any pdfs



Flashcard 7789043387660

Tags
#tensorflow #tensorflow-certificate
Question

Finding the best learning rate

#model
tf.random.set_seed(42) 
model_7 = tf.keras.Sequential([ tf.keras.layers.Dense(4, activation='relu'),
 tf.keras.layers.Dense(4, activation='relu'), 
tf.keras.layers.Dense(1, activation='sigmoid')
]) 

model_7.compile(optimizer=tf.keras.optimizers.Adam(), loss='binary_crossentropy', metrics=['accuracy'])


# callback
lr_scheduler = tf.keras.callbacks.LearningRateScheduler([...] epoch: 1e-4 * 10**(epoch/20)) 
history_7 = model_7.fit(X_train, y_train, epochs=100, callbacks=[lr_scheduler])




# plot learning rate vs the loss
plt.figure(figsize=(10, 7))
plt.semilogx(history_7.history['lr'], history_7.history['loss'])
plt.xlabel('Learning Rate')
plt.ylabel('Loss')
plt.title('Learning Rate vs Loss');
Answer
lambda

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
tivation='sigmoid') ]) model_7.compile(optimizer=tf.keras.optimizers.Adam(), loss='binary_crossentropy', metrics=['accuracy']) # callback lr_scheduler = tf.keras.callbacks.LearningRateScheduler(<span>lambda epoch: 1e-4 * 10**(epoch/20)) history_7 = model_7.fit(X_train, y_train, epochs=100, callbacks=[lr_scheduler]) # plot learning rate vs the loss plt.figure(figsize=(10, 7)) plt.semilogx(h

Original toplevel document

TfC_02_classification-PART_1
cision boundry plt.contourf(xx, yy, y_pred, cmap=plt.cm.RdYlBu, alpha=0.7) plt.scatter(X[:, 0], X[:, 1], c=y, s=40, cmap=plt.cm.RdYlBu) plt.xlim(xx.min(), xx.max()) plt.ylim(yy.min(), yy.max()) <span>Finding the best learning rate #model tf.random.set_seed(42) model_7 = tf.keras.Sequential([ tf.keras.layers.Dense(4, activation='relu'), tf.keras.layers.Dense(4, activation='relu'), tf.keras.layers.Dense(1, activation='sigmoid') ]) model_7.compile(optimizer=tf.keras.optimizers.Adam(), loss='binary_crossentropy', metrics=['accuracy']) # callback lr_scheduler = tf.keras.callbacks.LearningRateScheduler(lambda epoch: 1e-4 * 10**(epoch/20)) history_7 = model_7.fit(X_train, y_train, epochs=100, callbacks=[lr_scheduler]) # plot learning rate vs the loss plt.figure(figsize=(10, 7)) plt.semilogx(history_7.history['lr'], history_7.history['loss']) plt.xlabel('Learning Rate') plt.ylabel('Loss') plt.title('Learning Rate vs Loss'); <span>






Flashcard 7789045222668

Tags
#has-images #recurrent-neural-networks #rnn
[unknown IMAGE 7101515435276]
Question
These variable inputs enter the model through dedicated input layers at the top of the model’s architecture and are combined by simply concatenating them into a single [...]
Answer
long vector

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
These variable inputs enter the model through dedicated input layers at the top of the model’s architecture and are combined by simply concatenating them into a single long vector

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7789047581964

Tags
#ML-engineering #ML_in_Action #learning #machine #software-engineering
Question
ML engineers need just enough [...] to create plots and charts that communicate clearly what their research and models are doing, but not to develop dynamic web apps that have complex user experience (UX) components
Answer
visualization skills

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 just enough visualization skills to create plots and charts that communicate clearly what their research and models are doing, but not to develop dynamic web apps that have complex user experience (UX) components </spa

Original toplevel document (pdf)

cannot see any pdfs