Performing Advanced Feature Engineering in Keras Reviews

NICE

Sanal B. · Reviewed около 3 лет ago

Shivam P. · Reviewed около 3 лет ago

Yasin S. · Reviewed около 3 лет ago

Carolina G. · Reviewed около 3 лет ago

桢楠 蔡. · Reviewed около 3 лет ago

Gabriel G. · Reviewed около 3 лет 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 около 3 лет ago

JAYAVARAPU SIVA T. · Reviewed около 3 лет ago

Julia W. · Reviewed около 3 лет ago

Wijaya P. · Reviewed около 3 лет ago

good experience

saggurthi a. · Reviewed около 3 лет ago

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

Sadeka I. · Reviewed около 3 лет ago

Vishnu Teja R. · Reviewed около 3 лет ago

Manjesh G. · Reviewed около 3 лет ago

poornika b. · Reviewed около 3 лет ago

Giles W. · Reviewed около 3 лет ago

Marco C. · Reviewed около 3 лет ago

very useful

sathish s. · Reviewed около 3 лет ago

Ty S. · Reviewed около 3 лет ago

Koji H. · Reviewed около 3 лет ago

Xenon X. · Reviewed около 3 лет ago

Toshi S. · Reviewed около 3 лет 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 около 3 лет ago

Monjoy S. · Reviewed около 3 лет ago

Jonathan C. · Reviewed около 3 лет ago