Edited, memorised or added to reading queue

on 18-Oct-2024 (Fri)

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

Annotation 7629779897612

#deep #keras #learning #tensorflow #tfc-II
Model development for production continues to be a combination of automatic and hand-designed learning—which is often crucial for proprietary needs or advantages. But designing by hand does not mean starting from scratch; typically, you would start with a stock model and make tweaks and adjustments. To do this effectively, you need to know how the model works and why it works that way, the concepts that underlie its design, and the pros and cons of alternative building blocks you will learn from other SOTA models
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on

pdf

cannot see any pdfs



Flashcard 7656692387084

Tags
#deep-learning #has-images #keras #lstm #python #sequence
[unknown IMAGE 7104054824204]
Question
You can specify the input shape argument that expects a [...] containing the number of time steps and the number of features
Answer
tuple

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
You can specify the input shape argument that expects a tuple containing the number of time steps and the number of features

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7656707591436

Tags
#has-images #tensorflow #tensorflow-certificate
[unknown IMAGE 7626420784396]
Question

Deep Learning mantras: ;)

Building model: experiment
Evaluation model: [...]

Answer
visualize

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 mantras: ;) Building model: experiment Evaluation model: visualize

Original toplevel document

TfC 01 regression
more epochs, more data ### How? # from smaller model to larger model Evaluating models Typical workflow: build a model -> fit it -> evaulate -> tweak -> fit > evaluate -> .... <span>Building model: experiment Evaluation model: visualize What can visualize? the data model itself the training of a model predictions ## The 3 sets (or actually 2 sets: training and test set) tf.random.set_seed(999) X_train, X_test = tf.spli






Flashcard 7656708902156

Tags
#tensorflow #tensorflow-certificate
Question
[...]-score

Combination of precision and recall, ususally a good overall metric for classification models.

Answer
F1

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
F1-score Combination of precision and recall, ususally a good overall metric for classification models.

Original toplevel document

TfC_02_classification-PART_2
anced classes Precision For imbalanced class problems. Higher precision leads to less false positives. Recall Higher recall leads to less false negatives. Tradeoff between recall and precision. <span>F1-score Combination of precision and recall, ususally a good overall metric for classification models. keyboard_arrow_down Confusion matrix Can be hard to use whith large numbers of classes. y-axis -> true label x-axis -> predicted label # Create confusion metrics from sklearn.metr






Flashcard 7662104874252

Tags
#deep #keras #learning #tensorflow #tfc-II
Question
enterprise production is moving toward [...] for model development
Answer
automatic learning

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
enterprise production is moving toward automatic learning for model development

Original toplevel document (pdf)

cannot see any pdfs






Annotation 7662106709260

#RNN #ariadne #behaviour #consumer #deep-learning #priority #recurrent-neural-networks #retail #simulation #synthetic-data
Instead of absolute timestamps, the time differences ∆(x t−1 , x t ) to the previous inputs x t−1 are fed to the RNN at each time- step t.
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
al prediction of the RNN is linear in the learned and non-history features. The non-history features describe time, weekday, and behavioral gender and are also provided to the baseline methods. <span>Instead of absolute timestamps, the time differences ∆(x t−1 , x t ) to the previous inputs x t−1 are fed to the RNN at each time- step t. Furthermore, the difference between the last event x T and the prediction time (the session start) is provided to the final prediction layer <span>

Original toplevel document (pdf)

cannot see any pdfs



Flashcard 7662108806412

Tags
#RNN #ariadne #behaviour #consumer #deep-learning #priority #recurrent-neural-networks #retail #simulation #synthetic-data
Question
In e-commerce, available data sources and prediction scenarios often change, making the [...] of RNNs appealing as no problem-specific feature engineering has to take place.
Answer
generality

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
In e-commerce, available data sources and prediction scenarios often change, making the generality of RNNs appealing as no problem-specific feature engineering has to take place.

Original toplevel document (pdf)

cannot see any pdfs