Dense (fully connected) layers in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a dense layer with 10 units.

TensorFlow

layer = tf.keras.layers.Dense([1])

Drag options to blanks, or click blank then click option'

A0

BNone

C10

D5

Attempts:

3 left

💡 Hint

Common Mistakes

Using 0 or None will cause errors or no neurons to be created.

Choosing a smaller number like 5 does not meet the requirement.

The number 10 specifies the number of neurons in the dense layer.

2fill in blank

medium

Complete the code to add a ReLU activation to the dense layer.

TensorFlow

layer = tf.keras.layers.Dense(10, activation=[1])

Drag options to blanks, or click blank then click option'

A'relu'

B'sigmoid'

C'softmax'

D'tanh'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'sigmoid' or 'softmax' activates differently and are usually for output layers.

Forgetting quotes around the activation name causes syntax errors.

The 'relu' activation function is commonly used for hidden layers to add non-linearity.

3fill in blank

hard

Fix the error in the code by completing the missing argument for input shape.

TensorFlow

model = tf.keras.Sequential([
    tf.keras.layers.Dense(10, activation='relu', input_shape=[1])
])

Drag options to blanks, or click blank then click option'

A(10,)

B{10}

C[10]

D10

Attempts:

3 left

💡 Hint

Common Mistakes

Using an integer alone causes errors because shape must be a tuple.

Using list or set brackets is invalid for input_shape.

The input_shape argument expects a tuple describing the shape of each input sample.

4fill in blank

hard

Fill both blanks to create a model with two dense layers: first with 64 units and ReLU activation, second with 10 units and softmax activation.

TensorFlow

model = tf.keras.Sequential([
    tf.keras.layers.Dense([1], activation='relu'),
    tf.keras.layers.Dense([2], activation='softmax')
])

Drag options to blanks, or click blank then click option'

A64

B10

C32

D5

Attempts:

3 left

💡 Hint

Common Mistakes

Swapping the number of units between layers.

Using incorrect numbers like 32 or 5 which do not match the task.

The first dense layer has 64 units with ReLU activation, and the second has 10 units with softmax for classification.

5fill in blank

hard

Fill all three blanks to create a dense layer with 128 units, 'tanh' activation, and use it as the first layer with input shape (20,).

TensorFlow

model = tf.keras.Sequential([
    tf.keras.layers.Dense([1], activation=[2], input_shape=[3])
])

Drag options to blanks, or click blank then click option'

A128

B'tanh'

C(20,)

D'relu'

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong activation like 'relu' instead of 'tanh'.

Not using a tuple for input_shape.

Using wrong number of units.

The dense layer has 128 units, uses 'tanh' activation, and expects input samples shaped (20,).