Sequential model API in TensorFlow - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the Sequential model API in TensorFlow?

The Sequential model API is a simple way to build neural networks by stacking layers one after another in order. It is easy to use for beginners and works well for models with a single input and output.

beginner

How do you add layers to a Sequential model?

You add layers by calling the add() method on the Sequential model object, passing the layer you want to add, like model.add(tf.keras.layers.Dense(10)).

beginner

What is the difference between model.compile() and model.fit() in the Sequential API?

model.compile() sets up the learning process by specifying the optimizer, loss function, and metrics. model.fit() trains the model on data for a number of epochs.

intermediate

Can the Sequential model API handle models with multiple inputs or outputs?

No, the Sequential model API is designed for simple linear stacks of layers with one input and one output. For multiple inputs or outputs, use the Functional API instead.

beginner

Write a simple Sequential model with one hidden layer of 5 neurons and an output layer of 1 neuron.

import tensorflow as tf
model = tf.keras.Sequential()
model.add(tf.keras.layers.Dense(5, activation='relu', input_shape=(3,)))
model.add(tf.keras.layers.Dense(1))

What does the Sequential model API in TensorFlow represent?

A A tool for data preprocessing

B A graph of layers with multiple inputs

C A linear stack of layers

D A visualization library

The Sequential model API represents a linear stack of layers, where each layer has exactly one input and one output.

Which method is used to add layers to a Sequential model?

A add()

B append()

C add_layer()

D insert()

The method to add layers in a Sequential model is add().

Which method prepares the Sequential model for training by specifying optimizer and loss?

A model.fit()

B model.evaluate()

C model.predict()

D model.compile()

model.compile() sets the optimizer, loss function, and metrics before training.

Can the Sequential API handle models with multiple outputs?

A Yes, easily

B No, it only supports single input and output

C Yes, but only with special layers

D Only if you use callbacks

The Sequential API supports only one input and one output. For multiple outputs, use the Functional API.

What is the correct way to specify the input shape in the first layer of a Sequential model?

A input_shape=(number_of_features,)

B input_shape=[number_of_features]

C input_shape=number_of_features

D input_shape='number_of_features'

The input shape should be a tuple, e.g., input_shape=(3,) for 3 features.

Explain how to build and train a simple neural network using the Sequential model API in TensorFlow.

Think about the steps from model creation to training.

Describe the limitations of the Sequential model API and when you might need to use the Functional API instead.

Consider model complexity and input/output requirements.