Edited, memorised or added to reading queue

on 03-Aug-2025 (Sun)

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

Annotation 7720645823756

#feature-engineering #lstm #recurrent-neural-networks #rnn
There are examples of authors that used 274 features to predict customer behaviors in a non-contractual setting. One of the authors, who has extensive industry experience, has built predictive models with 600 features and more. Feature engineering is not only a time- consuming process, it is also error-prone, complex, and highly dependent on the analyst's domain knowledge (or, sometimes, lack thereof)
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
There are examples of authors that used 274 features to predict customer behaviors in a non-contractual setting. One of the authors, who has extensive industry experience, has built predictive models with 600 features and more. Feature engineering is not only a time- consuming process, it is also error-prone, complex, and highly dependent on the analyst's domain knowledge (or, sometimes, lack thereof). On the other hand, LSTM neural networks rely on raw unsummarized data to predict customer behaviors and can be scaled easily to very complex settings involving multiple streams of data

Original toplevel document (pdf)

cannot see any pdfs



Flashcard 7720648707340

Tags
#tensorflow #tensorflow-certificate
Question

[...] image classificaton: pizza, steak, sushi

Input_shape = [None, 224, 224, 3] - single image

Input shape = [32, 224, 224, 3] - common batch size of images

32 is a common batch size

Answer
Multiclass

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
Multiclass image classificaton: pizza, steak, sushi Input_shape = [None, 224, 224, 3] - single image Input shape = [32, 224, 224, 3] - common batch size of images 32 is a common batch size

Original toplevel document

TfC_02_classification-PART_1
ssification - a sample can be assigned to more than one label from more than 2 label options Multiclass classification - a sample can be assigned to one label but from more than 2 label options <span>Multiclass image classificaton: pizza, steak, sushi Input_shape = [None, 224, 224, 3] - single image Input shape = [32, 224, 224, 3] - common batch size of images 32 is a common batch size How to generate such data? from sklearn.datasets import make_circles # Make 1000 examples n_samples=1000 # Create circles X, y = make_circles(n_samples, noise=0.03, random_state=42) How