Performing Advanced Feature Engineering in Keras Reviews

Dani V. · Reviewed בערך 3 שנים ago

Akshay S. · Reviewed בערך 3 שנים ago

NICE

Sanal B. · Reviewed בערך 3 שנים ago

Shivam P. · Reviewed בערך 3 שנים ago

Yasin S. · Reviewed בערך 3 שנים ago

Carolina G. · Reviewed בערך 3 שנים ago

桢楠 蔡. · Reviewed בערך 3 שנים ago

Gabriel G. · Reviewed בערך 3 שנים ago

The transform function is a bit hard to comprehend. I suggest split it into two functions. The first one does the normalization and calculates euclidean distance. The second one creates the crossed feature.

Junhao Z. · Reviewed בערך 3 שנים ago

JAYAVARAPU SIVA T. · Reviewed בערך 3 שנים ago

Julia W. · Reviewed בערך 3 שנים ago

Wijaya P. · Reviewed בערך 3 שנים ago

good experience

saggurthi a. · Reviewed בערך 3 שנים ago

Some features, e.g., dayofweek and pickup_dropoff embedding features were defined but not used.

Sadeka I. · Reviewed בערך 3 שנים ago

Vishnu Teja R. · Reviewed בערך 3 שנים ago

Manjesh G. · Reviewed בערך 3 שנים ago

poornika b. · Reviewed בערך 3 שנים ago

Giles W. · Reviewed בערך 3 שנים ago

Marco C. · Reviewed בערך 3 שנים ago

very useful

sathish s. · Reviewed בערך 3 שנים ago

Ty S. · Reviewed בערך 3 שנים ago

Koji H. · Reviewed בערך 3 שנים ago

Xenon X. · Reviewed בערך 3 שנים ago

Toshi S. · Reviewed בערך 3 שנים ago

Just about enough time to complete. suggest to give 2 hours instead. Some questions: End of lab compares predicted taxi fare for both models with and without feature engineering. However there should be comparison back to either the actual taxi fare (if known) to see which model performs closer, or comparison using val RMSE for 2 models instead, or comparison of train/val loss/mse curves. Simply comparing 2 predicted taxi fares doesnt tell which performs better.

Joy L. · Reviewed בערך 3 שנים ago