Create a machine learning model of a real-life process or object : Adding More Metrics to Gain a Better Understanding

Why might clients require metrics other than mean absolute error?

• To reduce computation time

• To fit their specific use cases

• To better understand classification tasks

• To simplify the model

Which TensorFlow function can be used to list all available metrics?

• TF Keras metrics.tab()

• TF Keras metrics.show()

• TF Keras metrics.dot()

• TF Keras metrics.list()

What is the range of values for the R-squared metric?

• -1 to 1

• 0 to 1

• -1 to 0

• 0 to 100

What does an R-squared value below 0 indicate?

• The model is performing well

• The model is better than random predictions

• The model is worse than random predictions

• The model is perfectly accurate

Which TensorFlow functions are used to compute the residual in the R-squared metric?

• TF Add and TF Subtract

• TF Multiply and TF Divide

• TF Square and TF Reduce Sum

• TF Log and TF Exp

What is suggested to improve the R-squared score of a model?

• Use a smaller neural network

• Decrease the number of epochs

• Tune the activation functions

• Reduce the dataset size

What is the goal for the R-squared score mentioned in the video?

• To reach exactly 0.5

• To get a score of 1

• To achieve a score above 0.3

• To maintain a score below 0.2