First neural network in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a simple neural network model using TensorFlow Keras.

TensorFlow

import tensorflow as tf
model = tf.keras.Sequential([
    tf.keras.layers.Dense(10, activation=[1])
])

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

A"relu"

B"linear"

C"sigmoid"

D"softmax"

Attempts:

3 left

💡 Hint

Common Mistakes

Using activation functions like 'softmax' in the first hidden layer instead of output layer.

Forgetting to put activation function as a string.

The activation function "relu" is commonly used in the first layer of a neural network to introduce non-linearity.

2fill in blank

medium

Complete the code to compile the model with an optimizer.

TensorFlow

model.compile(optimizer=[1], loss='sparse_categorical_crossentropy', metrics=['accuracy'])

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

A"adagrad"

B"rmsprop"

C"adam"

D"sgd"

Attempts:

3 left

💡 Hint

Common Mistakes

Using an invalid string for optimizer.

Forgetting to put the optimizer name in quotes.

"adam" is a widely used optimizer that adapts the learning rate during training for better performance.

3fill in blank

hard

Fix the error in the code to train the model on data.

TensorFlow

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

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

A5

B"5"

C10.0

DNone

Attempts:

3 left

💡 Hint

Common Mistakes

Passing epochs as a string like "5" instead of integer 5.

Passing epochs as a float like 10.0.

The epochs parameter must be an integer specifying how many times the model sees the entire dataset.

4fill in blank

hard

Fill both blanks to create a dictionary of training accuracy and loss from the history object.

TensorFlow

metrics = { 'accuracy': history.history[[1]], 'loss': history.history[[2]] }

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

A"accuracy"

B"acc"

C"loss"

D"val_loss"

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'acc' instead of 'accuracy' which may not be present depending on TensorFlow version.

Mixing validation loss key 'val_loss' with training loss.

The keys 'accuracy' and 'loss' in history.history store the training accuracy and loss values respectively.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps each word to its length if length is greater than 3.

TensorFlow

lengths = { [1]: [2] for [3] in words if len([3]) > 3 }

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

Aword

Blen(word)

Ditem

Attempts:

3 left

💡 Hint

Common Mistakes

Using different variable names inconsistently.

Not using len() to get the length.

This dictionary comprehension creates keys as words and values as their lengths, filtering words longer than 3 characters.