Why training optimizes model weights in TensorFlow - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a simple model with one dense layer.

TensorFlow

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

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

A1

B5

C3

D10

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing too many units for a simple output layer.

The model has one dense layer with 1 output unit, matching a simple regression or binary output.

2fill in blank

medium

Complete the code to compile the model with mean squared error loss.

TensorFlow

model.compile(optimizer='adam', loss='[1]')

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

Abinary_crossentropy

Bhinge

Cmean_squared_error

Dcategorical_crossentropy

Attempts:

3 left

💡 Hint

Common Mistakes

Using classification loss functions for regression.

Mean squared error is used for regression tasks to measure the difference between predicted and true values.

3fill in blank

hard

Fix the error in the training code by filling the correct method name.

TensorFlow

history = model.[1](x_train, y_train, epochs=5)

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

Afit

Btrain

Crun

Dexecute

Attempts:

3 left

💡 Hint

Common Mistakes

Using non-existent methods like 'train' or 'run'.

The correct method to train a TensorFlow Keras model is fit.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that stores squared values for even numbers.

TensorFlow

squares = {x: x[1]2 for x in range(1, 6) if x [2] 2 == 0}

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

A**

B%

C//

D+

Attempts:

3 left

💡 Hint

Common Mistakes

Using '+' instead of '**' for squaring.

Using '//' instead of '%' for checking evenness.

Use ** to square numbers and % to check if a number is even (remainder 0).

5fill in blank

hard

Fill all three blanks to create a filtered dictionary with uppercase keys and values greater than zero.

TensorFlow

result = [1]: [2] for k, v in data.items() if v [3] 0}

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

Ak.upper()

Bv

C>

Dk

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'k' instead of 'k.upper()' for keys.

Using '<' instead of '>' for filtering.

Keys are converted to uppercase with k.upper(), values are kept as v, and filtered where v > 0.