Multi-class classification model in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Model Choice

intermediate

Choosing the correct output layer for multi-class classification

You want to build a neural network in TensorFlow to classify images into 5 different categories. Which output layer configuration is correct for this multi-class classification task?

A Dense(5, activation='softmax')

B Dense(1, activation='sigmoid')

C Dense(1, activation='softmax')

D Dense(5, activation='sigmoid')

💡 Hint

For multi-class classification, the output layer should have one neuron per class with a softmax activation.

Softmax activation outputs probabilities for each class summing to 1, which is needed for multi-class classification. Sigmoid is for binary or multi-label tasks.

❓ Metrics

intermediate

Correct loss function for multi-class classification

Which loss function should you use in TensorFlow when training a multi-class classification model with one-hot encoded labels?

A tf.keras.losses.SparseCategoricalCrossentropy()

B tf.keras.losses.BinaryCrossentropy()

C tf.keras.losses.MeanSquaredError()

D tf.keras.losses.CategoricalCrossentropy()

💡 Hint

One-hot encoded labels require a loss function that compares probability distributions.

CategoricalCrossentropy is used with one-hot labels. SparseCategoricalCrossentropy is for integer labels. BinaryCrossentropy is for binary tasks.

❓ Predict Output

advanced

Output shape of model predictions

Given the following TensorFlow model for 4-class classification, what is the shape of the output predictions for a batch of 10 samples?

TensorFlow

import tensorflow as tf
model = tf.keras.Sequential([
    tf.keras.layers.Dense(16, activation='relu', input_shape=(8,)),
    tf.keras.layers.Dense(4, activation='softmax')
])
import numpy as np
sample_input = np.random.random((10, 8))
predictions = model(sample_input)
predictions_shape = predictions.shape

A (10, 4)

B (4, 10)

C (10, 1)

D (1, 4)

💡 Hint

The output shape matches the batch size and number of classes.

For 10 samples and 4 classes, the output shape is (10, 4), each row is a probability distribution over classes.

❓ Hyperparameter

advanced

Effect of batch size on training stability

In training a multi-class classification model, what is a common effect of increasing the batch size too much?

A Training becomes more noisy and always improves generalization

B Model always overfits immediately

C Training becomes less noisy but may converge to sharp minima causing worse generalization

D Training speed decreases significantly without affecting accuracy

💡 Hint

Think about how batch size affects gradient noise and generalization.

Larger batch sizes reduce gradient noise, which can lead to convergence to sharp minima and worse generalization.

🔧 Debug

expert

Identifying the cause of poor multi-class model accuracy

You trained a multi-class classification model with 3 classes using one-hot encoded labels. The model's accuracy stays around 33% (random guess). Which of the following is the most likely cause?

A Using CategoricalCrossentropy loss with one-hot encoded labels

B Using SparseCategoricalCrossentropy loss with one-hot encoded labels

C Using softmax activation in the output layer

D Using Adam optimizer

💡 Hint

Check if the loss function matches the label format.

SparseCategoricalCrossentropy expects integer labels, not one-hot. Using it with one-hot labels causes poor training and accuracy.