Which model is appropriate for a plain stack of layers
Neural Networks with TF2 and Keras >>> Which model is appropriate for a plain stack of layers >>> Introduction to TensorFlow
1.
Question 1
Which model is appropriate for a plain stack of layers ?
1 / 1 point
Sequential
Functional
None of the above.
=========================================
4.
Question 4
What are the parameters involved while compiling the Keras model?
1 / 1 point
Optimizer
Loss function
Evaluation metrics
All of the above.
=========================================
6.
Question 6
What are the weaknesses of the Keras Functional API?
1 / 1 point
It doesn’t support dynamic architectures. The Functional API treats models as DAGs of layers. This is true for most deep learning architectures, but not all: for instance, recursive networks or Tree RNNs do not follow this assumption and cannot be implemented in the Functional API.
Sometimes we have to write from scratch and need to build subclasses. When writing advanced achitectures, you may want to do things that are outside the scope of “defining a DAG of layers”: for instance, you may want to expose multiple custom training and inference methods on your model instance. This requires subclassing.
Both A & B
None of the above
=========================================
3.
Question 3
The predict function in the tf.keras API returns what?
1 / 1 point
Numpy array(s) of predictions
Input_samples of predictions
Both A & B
None of the above
=========================================
5.
Question 5
What is the significance of the Fit method while training a Keras model ?
1 / 1 point
Defines the number of steps per epochs
Defines the number of epochs
Define the validation steps
Defines the batch size
=========================================
2.
Question 2
How does Adam (optimization algorithm) help in compiling the Keras model?
1 / 1 point
By updating network weights iteratively based on training data.