Performing Advanced Feature Engineering in Keras Reviews

NICE

Sanal B. · Reviewed yaklaşık 3 yıl ago

Shivam P. · Reviewed yaklaşık 3 yıl ago

Yasin S. · Reviewed yaklaşık 3 yıl ago

Carolina G. · Reviewed yaklaşık 3 yıl ago

桢楠 蔡. · Reviewed yaklaşık 3 yıl ago

Gabriel G. · Reviewed yaklaşık 3 yıl 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 yaklaşık 3 yıl ago

JAYAVARAPU SIVA T. · Reviewed yaklaşık 3 yıl ago

Julia W. · Reviewed yaklaşık 3 yıl ago

Wijaya P. · Reviewed yaklaşık 3 yıl ago

good experience

saggurthi a. · Reviewed yaklaşık 3 yıl ago

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

Sadeka I. · Reviewed yaklaşık 3 yıl ago

Vishnu Teja R. · Reviewed yaklaşık 3 yıl ago

Manjesh G. · Reviewed yaklaşık 3 yıl ago

poornika b. · Reviewed yaklaşık 3 yıl ago

Giles W. · Reviewed yaklaşık 3 yıl ago

Marco C. · Reviewed yaklaşık 3 yıl ago

very useful

sathish s. · Reviewed yaklaşık 3 yıl ago

Ty S. · Reviewed yaklaşık 3 yıl ago

Koji H. · Reviewed yaklaşık 3 yıl ago

Xenon X. · Reviewed yaklaşık 3 yıl ago

Toshi S. · Reviewed yaklaşık 3 yıl 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 yaklaşık 3 yıl ago

Monjoy S. · Reviewed yaklaşık 3 yıl ago

Jonathan C. · Reviewed yaklaşık 3 yıl ago