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.

Practice

1. What activation function is commonly used in the output layer of a binary classification model in TensorFlow?

easy

A. Tanh

B. ReLU

C. Softmax

D. Sigmoid

Solution

1. Step 1: Understand output layer role in binary classification

   The output layer must produce a probability between 0 and 1 to represent two classes.

2. Step 2: Identify suitable activation function

   Sigmoid activation compresses output to range [0, 1], perfect for binary decisions.

3. Final Answer:

   Sigmoid -> Option D

4. Quick Check:

   Binary output needs sigmoid = Sigmoid [OK]

Hint: Binary output needs sigmoid activation [OK]

Common Mistakes:

• Using softmax for binary output
• Using ReLU which outputs unbounded values
• Using tanh which outputs between -1 and 1

2. Which of the following is the correct way to compile a binary classification model in TensorFlow?

easy

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

B. model.compile(optimizer='rmsprop', loss='hinge', metrics=['accuracy'])

C. model.compile(optimizer='sgd', loss='mean_squared_error', metrics=['accuracy'])

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

Solution

1. Step 1: Identify appropriate loss for binary classification

   Binary classification requires 'binary_crossentropy' loss to measure error correctly.

2. Step 2: Check optimizer and metrics

   'adam' optimizer and 'accuracy' metric are standard choices for training and evaluation.

3. Final Answer:

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

4. Quick Check:

   Binary loss = binary_crossentropy [OK]

Hint: Use binary_crossentropy loss for binary classification [OK]

Common Mistakes:

• Using categorical_crossentropy for binary tasks
• Using mean_squared_error which is for regression
• Choosing hinge loss which is for SVMs

3. Given the following TensorFlow model code, what will be the shape of the output layer?

model = tf.keras.Sequential([
  tf.keras.layers.Dense(10, activation='relu', input_shape=(5,)),
  tf.keras.layers.Dense(1, activation='sigmoid')
])

medium

A. (None, 1)

B. (None, 10)

C. (5, 1)

D. (1,)

Solution

1. Step 1: Analyze the last layer configuration

   The last Dense layer has 1 unit and sigmoid activation, so output shape is (batch_size, 1).

2. Step 2: Understand batch dimension placeholder

   TensorFlow uses None for batch size, so output shape is (None, 1).

3. Final Answer:

   (None, 1) -> Option A

4. Quick Check:

   Output units = 1 means shape = (None, 1) [OK]

Hint: Output shape matches last layer units with batch size None [OK]

Common Mistakes:

• Confusing input shape with output shape
• Ignoring batch size dimension
• Assuming output shape is (1,) without batch

4. You trained a binary classification model but the accuracy stays around 50% after many epochs. Which fix is most likely to improve the model?

medium

A. Change the output activation to softmax

B. Use binary_crossentropy loss instead of categorical_crossentropy

C. Increase the batch size to 1024

D. Remove the activation function from the output layer

Solution

1. Step 1: Identify the cause of poor accuracy

   Using categorical_crossentropy loss with a single sigmoid output causes wrong loss calculation.

2. Step 2: Apply correct loss function

   Switching to binary_crossentropy aligns loss with sigmoid output for binary classification.

3. Final Answer:

   Use binary_crossentropy loss instead of categorical_crossentropy -> Option B

4. Quick Check:

   Loss must match output activation [OK]

Hint: Match loss to output activation for correct training [OK]

Common Mistakes:

• Using softmax for binary output
• Removing output activation causing invalid probabilities
• Assuming batch size alone fixes accuracy

5. You want to build a binary classification model to predict if an email is spam or not. Your dataset has 1000 samples with 20 features each. Which model architecture and compile settings are best?

hard

A. Sequential model with one Dense layer (1 unit, sigmoid), compile with binary_crossentropy and adam

B. Sequential model with one Dense layer (20 units, softmax), compile with categorical_crossentropy and sgd

C. Sequential model with two Dense layers (10 units relu, then 1 unit sigmoid), compile with binary_crossentropy and adam

D. Sequential model with three Dense layers (64 relu, 32 relu, 1 tanh), compile with mean_squared_error and rmsprop

Solution

1. Step 1: Choose model complexity for dataset size

   Two layers with relu then sigmoid balance learning capacity and binary output.

2. Step 2: Select correct loss and optimizer

   Binary_crossentropy fits binary tasks; adam optimizer adapts well for small datasets.

3. Final Answer:

   Sequential model with two Dense layers (10 units relu, then 1 unit sigmoid), compile with binary_crossentropy and adam -> Option C

4. Quick Check:

   Two layers + sigmoid + binary_crossentropy = Best practice [OK]

Hint: Use relu hidden layers + sigmoid output + binary_crossentropy [OK]

Common Mistakes:

• Using softmax for binary classification
• Using tanh output activation
• Using mean_squared_error loss for classification