关于“Performing Advanced Feature Engineering in Keras”的评价

NICE

Sanal B. · 已于 about 3 years前审核

Shivam P. · 已于 about 3 years前审核

Yasin S. · 已于 about 3 years前审核

Carolina G. · 已于 about 3 years前审核

桢楠 蔡. · 已于 about 3 years前审核

Gabriel G. · 已于 about 3 years前审核

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. · 已于 about 3 years前审核

JAYAVARAPU SIVA T. · 已于 about 3 years前审核

Julia W. · 已于 about 3 years前审核

Wijaya P. · 已于 about 3 years前审核

good experience

saggurthi a. · 已于 about 3 years前审核

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

Sadeka I. · 已于 about 3 years前审核

Vishnu Teja R. · 已于 about 3 years前审核

Manjesh G. · 已于 about 3 years前审核

poornika b. · 已于 about 3 years前审核

Giles W. · 已于 about 3 years前审核

Marco C. · 已于 about 3 years前审核

very useful

sathish s. · 已于 about 3 years前审核

Ty S. · 已于 about 3 years前审核

Koji H. · 已于 about 3 years前审核

Xenon X. · 已于 about 3 years前审核

Toshi S. · 已于 about 3 years前审核

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. · 已于 about 3 years前审核

Monjoy S. · 已于 about 3 years前审核

Jonathan C. · 已于 about 3 years前审核