Binary classification model in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of a simple binary classification model training

Consider the following TensorFlow code that trains a binary classification model on dummy data. What will be the printed training accuracy after 5 epochs?

TensorFlow

import tensorflow as tf
import numpy as np

# Create dummy data
x_train = np.random.random((100, 10))
y_train = np.random.randint(2, size=(100, 1))

# Build a simple model
model = tf.keras.Sequential([
    tf.keras.layers.Dense(8, activation='relu', input_shape=(10,)),
    tf.keras.layers.Dense(1, activation='sigmoid')
])

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

history = model.fit(x_train, y_train, epochs=5, batch_size=10, verbose=0)

print(f"Training accuracy after 5 epochs: {history.history['accuracy'][-1]:.2f}")

A Training accuracy after 5 epochs: 0.50

B Training accuracy after 5 epochs: 0.90

C Training accuracy after 5 epochs: 0.10

D Training accuracy after 5 epochs: 1.00

💡 Hint

The data is random and labels are random, so the model cannot learn meaningful patterns.

Since the input data and labels are random, the model cannot find patterns to improve accuracy. The accuracy will stay close to random guessing, about 50%.

❓ Model Choice

intermediate

Choosing the correct output layer for binary classification

Which output layer configuration is correct for a binary classification model in TensorFlow?

A tf.keras.layers.Dense(2, activation='softmax')

B tf.keras.layers.Dense(1, activation='sigmoid')

C tf.keras.layers.Dense(1, activation='softmax')

D tf.keras.layers.Dense(2, activation='sigmoid')

💡 Hint

Binary classification usually uses one output neuron with a sigmoid activation.

For binary classification, the output layer should have one neuron with sigmoid activation to output a probability between 0 and 1.

❓ Hyperparameter

advanced

Best loss function for binary classification

Which loss function is most appropriate when training a binary classification model with a sigmoid output in TensorFlow?

A tf.keras.losses.BinaryCrossentropy()

B tf.keras.losses.CategoricalCrossentropy()

C tf.keras.losses.MeanSquaredError()

D tf.keras.losses.SparseCategoricalCrossentropy()

💡 Hint

Binary classification with sigmoid output requires a loss that handles probabilities for two classes.

BinaryCrossentropy is designed for binary classification problems with sigmoid outputs, measuring the difference between true labels and predicted probabilities.

❓ Metrics

advanced

Interpreting model accuracy on imbalanced binary data

A binary classification model is trained on a dataset where 95% of samples belong to class 0 and 5% to class 1. The model always predicts class 0. What accuracy will the model achieve?

A 0.50

B 0.05

C 1.00

D 0.95

💡 Hint

Accuracy counts how many predictions match true labels.

Since 95% of samples are class 0, always predicting class 0 yields 95% accuracy, but the model fails to detect class 1.

🔧 Debug

expert

Identifying the error in binary classification model compilation

What error will this TensorFlow code raise when compiling a binary classification model?

TensorFlow

import tensorflow as tf

model = tf.keras.Sequential([
    tf.keras.layers.Dense(16, activation='relu', input_shape=(20,)),
    tf.keras.layers.Dense(1, activation='sigmoid')
])

model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

A RuntimeError: Activation function 'sigmoid' not supported with categorical_crossentropy.

B TypeError: optimizer argument must be a string or tf.keras.optimizers.Optimizer instance.

C ValueError: You are passing a target array of shape (None, 1) while using categorical_crossentropy loss. Expected shape is (None, num_classes).

D No error, code compiles successfully.

💡 Hint

Check if the loss function matches the output layer and label format.

Using 'categorical_crossentropy' with a single sigmoid output neuron causes a shape mismatch error because categorical_crossentropy expects one-hot encoded labels and multiple output neurons.