ML quiz 5

Select the option(s) that complete the following sentence correctly. Tf.keras is:

• the TensorFlow variant of the open-source Keras API

• an implementation of the Keras API

• the Keras variant of the open-source TensorFlow API

• an end-to-end open-source platform for machine learning

• a high-level API for TensorFlow

The core of NumPy is well-optimized _______ code:

• C++

• C

• python

• Java

• assembly

Pandas is __________

• development tool that gives web developers a framework, providing structure for all the code they write.

• useful for creating n-dimensional arrays and numerical computing tools

• useful for creating an easy way to represent datasets in memory.

• a library used for scientific and technical computing

Generalization allows getting 100% accuracy by creating complex models.

• True

• False

Ockham’s Razor principle says that a model should be as _______ as possible.

• Complex

• Creative

• Representative

• Simple

Which one of the below examples would violate one of the ML basic assumptions: the distributions being stationary?

• The user behavior changes between different seasons

• If people suddenly decide that a different breed of puppies is as cute as they saw before

An overfitting model ________

• Gets a high loss during training but does a good job predicting new data

• Gets a high loss during training and does a poor job predicting new data

• Gets a low loss during training but does a poor job predicting new data

• Gets a low loss during training and does a good job predicting new data

An under-fitting model ______

• Gets a high loss during training but does a good job predicting new data

• Gets a high loss during training and does a poor job predicting new data

• Gets a low loss during training but does a poor job predicting new data

• Gets a low loss during training and does a good job predicting new data

Overfitting occurs due to _____

• Low variance

• High variance

• Low bias

• High bias

Underfitting occurs due to ______

• High bias

• High variance

• Low bias

• Low variance