Loss functions (MSE, cross-entropy) in TensorFlow - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the purpose of a loss function in machine learning?

A loss function measures how well a model's predictions match the actual data. It tells the model how wrong it is so it can learn and improve.

beginner

Explain Mean Squared Error (MSE) loss function.

MSE calculates the average of the squares of the differences between predicted and actual values. It punishes bigger errors more, helping models learn precise predictions.

beginner

What type of problems is cross-entropy loss used for?

Cross-entropy loss is used for classification problems. It measures how close the predicted probabilities are to the actual class labels.

intermediate

How does cross-entropy loss handle predictions that are very wrong?

Cross-entropy loss gives a high penalty when the predicted probability for the true class is very low, encouraging the model to predict probabilities closer to the true labels.

beginner

Show a simple TensorFlow code snippet to compute MSE loss.

import tensorflow as tf

true = tf.constant([3.0, -0.5, 2.0, 7.0])
pred = tf.constant([2.5, 0.0, 2.0, 8.0])

mse = tf.reduce_mean(tf.square(pred - true))
print(f'MSE Loss: {mse.numpy()}')

Which loss function is best suited for a regression problem?

A Cross-entropy

B Categorical accuracy

C Hinge loss

D Mean Squared Error (MSE)

MSE is used for regression because it measures the average squared difference between predicted and actual continuous values.

Cross-entropy loss is mainly used for which type of machine learning task?

A Classification

B Regression

C Clustering

D Dimensionality reduction

Cross-entropy loss measures the difference between predicted probabilities and actual class labels, making it ideal for classification.

What does a high cross-entropy loss value indicate?

A Predictions are very close to true labels

B Predictions are very wrong

C Model is perfectly trained

D Loss function is not working

A high cross-entropy loss means the predicted probabilities are far from the true labels, indicating poor predictions.

In TensorFlow, which function can be used to compute MSE loss manually?

A tf.reduce_mean(tf.square(y_true - y_pred))

B tf.nn.softmax_cross_entropy_with_logits

C tf.argmax

D tf.reduce_sum(y_true + y_pred)

MSE is computed by averaging the squared differences between true and predicted values using tf.reduce_mean and tf.square.

Which loss function punishes bigger errors more strongly?

A Cross-entropy

B Mean Absolute Error

C Mean Squared Error

D Hinge loss

MSE squares the errors, so larger errors have a bigger impact on the loss value.

Describe how Mean Squared Error (MSE) and cross-entropy loss differ in their use and calculation.

Think about the type of problem and how errors are measured.

Explain why loss functions are important in training machine learning models.

Consider the role of feedback in learning.

Practice

1. Which loss function is best suited for predicting continuous numbers in TensorFlow?

easy

A. Mean Squared Error (MSE)

B. Categorical Cross-Entropy

C. Binary Cross-Entropy

D. Hinge Loss

Solution

1. Step 1: Understand the type of prediction

   Continuous number prediction means the output is a real number, not categories.

2. Step 2: Match loss function to prediction type

   MSE calculates the average squared difference between predicted and true numbers, ideal for continuous values.

3. Final Answer:

   Mean Squared Error (MSE) -> Option A

4. Quick Check:

   Continuous output = MSE [OK]

Hint: Use MSE for numbers, cross-entropy for categories [OK]

Common Mistakes:

• Using cross-entropy for number prediction
• Confusing binary and categorical cross-entropy
• Choosing hinge loss for regression

2. Which of the following is the correct way to use Mean Squared Error loss in TensorFlow?

easy

A. tf.keras.losses.BinaryCrossentropy()

B. tf.losses.CrossEntropy()

C. tf.keras.losses.MeanSquaredError()

D. tf.losses.MSE()

Solution

1. Step 1: Recall TensorFlow loss function syntax

   TensorFlow uses tf.keras.losses.MeanSquaredError() for MSE loss.

2. Step 2: Check options for correct function name and module

   tf.keras.losses.MeanSquaredError() matches the correct full name and module; others are either wrong names or modules.

3. Final Answer:

   tf.keras.losses.MeanSquaredError() -> Option C

4. Quick Check:

   Correct MSE syntax = tf.keras.losses.MeanSquaredError() [OK]

Hint: Use tf.keras.losses for standard loss functions [OK]

Common Mistakes:

• Using tf.losses instead of tf.keras.losses
• Wrong function names like CrossEntropy for MSE
• Missing parentheses when creating loss object

3. What will be the output loss value when using Mean Squared Error loss in TensorFlow for predictions [2.0, 3.0] and true values [1.0, 5.0]?

medium

A. 1.5

B. 3.0

C. 4.0

D. 2.5

Solution

1. Step 1: Calculate squared errors for each prediction

   (2.0 - 1.0)^2 = 1.0, (3.0 - 5.0)^2 = 4.0

2. Step 2: Compute mean of squared errors

   (1.0 + 4.0) / 2 = 2.5

3. Step 3: Verify options

   2.5 matches 2.5, but check carefully: The question asks for output loss value from TensorFlow's MSE which returns mean, so 2.5 is correct.

4. Final Answer:

   2.5 -> Option D

5. Quick Check:

   MSE = mean squared error = 2.5 [OK]

Hint: Square errors, then average them for MSE [OK]

Common Mistakes:

• Summing errors without averaging
• Taking absolute difference instead of squared
• Mixing up predicted and true values

4. Identify the error in this TensorFlow code snippet using categorical cross-entropy loss:

model.compile(optimizer='adam', loss=tf.keras.losses.CategoricalCrossentropy, metrics=['accuracy'])

medium

A. Missing parentheses after CategoricalCrossentropy

B. Wrong optimizer name

C. Metrics should be 'loss' not 'accuracy'

D. Loss function should be a string, not an object

Solution

1. Step 1: Check loss function usage in compile

   Loss functions must be called as objects, so parentheses are needed.

2. Step 2: Identify missing parentheses

   tf.keras.losses.CategoricalCrossentropy is a class; missing () means passing the class, not an instance.

3. Final Answer:

   Missing parentheses after CategoricalCrossentropy -> Option A

4. Quick Check:

   Loss function needs () to create instance [OK]

Hint: Always add () when passing loss function classes [OK]

Common Mistakes:

• Forgetting parentheses on loss functions
• Confusing optimizer names
• Using wrong metric names

5. You have a multi-class classification problem with 4 classes. Which loss function and output layer activation should you use in TensorFlow for best results?

hard

A. Use Mean Squared Error loss with sigmoid activation

B. Use Categorical Cross-Entropy loss with softmax activation

C. Use Binary Cross-Entropy loss with softmax activation

D. Use Hinge loss with linear activation

Solution

1. Step 1: Identify problem type and output requirements

   Multi-class classification with 4 classes requires probabilities summing to 1.

2. Step 2: Match loss and activation functions

   Softmax activation outputs probabilities for each class; categorical cross-entropy measures loss for multi-class.

3. Final Answer:

   Use Categorical Cross-Entropy loss with softmax activation -> Option B

4. Quick Check:

   Multi-class = softmax + categorical cross-entropy [OK]

Hint: Softmax + categorical cross-entropy for multi-class [OK]

Common Mistakes:

• Using MSE for classification
• Using sigmoid for multi-class output
• Using binary cross-entropy for multi-class