Custom loss functions in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to define a custom loss function that calculates mean squared error.

TensorFlow

def custom_loss(y_true, y_pred):
    return tf.reduce_mean(tf.square(y_true [1] y_pred))

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

A-

B+

C/

D*

Attempts:

3 left

💡 Hint

Common Mistakes

Using addition instead of subtraction

Using multiplication or division instead of subtraction

The mean squared error loss calculates the average of the squared differences between true and predicted values. We subtract y_pred from y_true before squaring.

2fill in blank

medium

Complete the code to define a custom loss function that returns the mean absolute error.

TensorFlow

def custom_loss(y_true, y_pred):
    return tf.reduce_mean(tf.abs(y_true [1] y_pred))

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

A-

B+

C*

D/

Attempts:

3 left

💡 Hint

Common Mistakes

Using addition instead of subtraction

Using multiplication or division instead of subtraction

Mean absolute error calculates the average of the absolute differences between true and predicted values. We subtract y_pred from y_true before taking the absolute value.

3fill in blank

hard

Fix the error in the custom loss function that calculates mean squared logarithmic error.

TensorFlow

def custom_loss(y_true, y_pred):
    return tf.reduce_mean(tf.square(tf.math.log1p(y_true) [1] tf.math.log1p(y_pred)))

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

A+

B*

C-

D/

Attempts:

3 left

💡 Hint

Common Mistakes

Using addition instead of subtraction

Using multiplication or division instead of subtraction

Mean squared logarithmic error calculates the average squared difference of the log-transformed true and predicted values. We subtract the logs before squaring.

4fill in blank

hard

Fill both blanks to create a custom loss function that calculates weighted mean squared error.

TensorFlow

def custom_loss(y_true, y_pred, weights):
    error = y_true [1] y_pred
    weighted_error = tf.multiply(tf.square(error), [2])
    return tf.reduce_mean(weighted_error)

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

A-

B+

Cweights

Dy_true

Attempts:

3 left

💡 Hint

Common Mistakes

Adding instead of subtracting for error

Multiplying by wrong variable instead of weights

Weighted mean squared error multiplies the squared error by weights before averaging. We subtract y_pred from y_true to get the error, square it, then multiply by weights.

5fill in blank

hard

Fill all three blanks to define a custom loss function that combines mean squared error and mean absolute error with a balancing factor.

TensorFlow

def custom_loss(y_true, y_pred, alpha):
    mse = tf.reduce_mean(tf.square(y_true [1] y_pred))
    mae = tf.reduce_mean(tf.abs(y_true [2] y_pred))
    return [3] * mse + (1 - [3]) * mae

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

A-

B+

Calpha

D*

Attempts:

3 left

💡 Hint

Common Mistakes

Using addition instead of subtraction for error calculations

Using wrong variable instead of alpha for balancing

This custom loss combines mean squared error (MSE) and mean absolute error (MAE) using a balancing factor alpha. Both errors use subtraction between true and predicted values.

Practice

1. What is the main purpose of a custom loss function in TensorFlow?

easy

A. To change the model's architecture layers

B. To generate new training data from existing data

C. To speed up the training process automatically

D. To define a special way to measure how wrong the model's predictions are

Solution

1. Step 1: Understand the role of loss functions

   Loss functions measure how far the model's predictions are from the true values.

2. Step 2: Identify what custom loss functions do

   Custom loss functions let you define your own way to measure this error, which can help in special cases.

3. Final Answer:

   To define a special way to measure how wrong the model's predictions are -> Option D

4. Quick Check:

   Custom loss = custom error measure [OK]

Hint: Loss functions measure error; custom ones define your own error [OK]

Common Mistakes:

• Confusing loss function with model architecture
• Thinking loss speeds up training automatically
• Mixing loss function with data generation

2. Which of the following is the correct way to define a simple custom loss function in TensorFlow using Python?

easy

A. def custom_loss(y_true, y_pred): return tf.add(y_true, y_pred)

B. def custom_loss(y_true, y_pred): return y_true + y_pred

C. def custom_loss(y_true, y_pred): return tf.reduce_mean(tf.square(y_true - y_pred))

D. def custom_loss(y_true, y_pred): return tf.matmul(y_true, y_pred)

Solution

1. Step 1: Check the function signature

   The function must take true and predicted values as inputs.

2. Step 2: Verify the loss calculation

   Loss should measure error, e.g., mean squared error: mean of squared differences.

3. Final Answer:

   def custom_loss(y_true, y_pred): return tf.reduce_mean(tf.square(y_true - y_pred)) -> Option C

4. Quick Check:

   Loss = mean squared error formula [OK]

Hint: Loss = mean of squared differences for regression [OK]

Common Mistakes:

• Returning sum instead of mean
• Adding true and predicted values instead of difference
• Using matrix multiplication instead of error calculation

3. Given the following custom loss function, what will be the output if y_true = [2.0, 3.0] and y_pred = [1.0, 5.0]?

def custom_loss(y_true, y_pred):
    return tf.reduce_sum(tf.abs(y_true - y_pred))

medium

A. 3.0

B. 4.0

C. 5.0

D. 6.0

Solution

1. Step 1: Calculate absolute differences

   abs(2.0 - 1.0) = 1.0 and abs(3.0 - 5.0) = 2.0

2. Step 2: Sum the absolute differences

   1.0 + 2.0 = 3.0

3. Final Answer:

   3.0 -> Option A

4. Quick Check:

   Sum of absolute errors = 3.0 [OK]

Hint: Sum absolute differences for this loss [OK]

Common Mistakes:

• Confusing sum with mean
• Using squared differences instead of absolute
• Mixing up true and predicted values

4. Identify the error in this custom loss function and select the correct fix:

def custom_loss(y_true, y_pred):
    return tf.reduce_mean(y_true - y_pred)

medium

A. Change function to return y_true + y_pred

B. Use absolute difference or squared difference instead of direct subtraction

C. Remove tf.reduce_mean and return raw difference

D. Use tf.matmul instead of subtraction

Solution

1. Step 1: Understand the problem with direct subtraction

   Direct subtraction can give positive and negative values that cancel out, not measuring error properly.

2. Step 2: Correct the loss calculation

   Use absolute value or square the difference to measure error magnitude correctly.

3. Final Answer:

   Use absolute difference or squared difference instead of direct subtraction -> Option B

4. Quick Check:

   Loss must measure error magnitude, not signed difference [OK]

Hint: Loss must be positive; use abs() or square() [OK]

Common Mistakes:

• Returning signed difference causing cancellation
• Removing mean reduces loss meaning
• Using matrix multiplication wrongly

5. You want to create a custom loss function that penalizes under-predictions more than over-predictions. Which of the following custom loss functions achieves this behavior correctly?

hard

A. def custom_loss(y_true, y_pred): return tf.reduce_mean(tf.where(y_pred < y_true, 2 * (y_true - y_pred), y_pred - y_true))

B. def custom_loss(y_true, y_pred): return tf.reduce_mean(tf.abs(y_true - y_pred))

C. def custom_loss(y_true, y_pred): return tf.reduce_mean(tf.square(y_true - y_pred))

D. def custom_loss(y_true, y_pred): return tf.reduce_sum(y_pred - y_true)

Solution

1. Step 1: Understand the requirement

   We want to penalize under-predictions (y_pred < y_true) more than over-predictions.

2. Step 2: Analyze each option

   def custom_loss(y_true, y_pred): return tf.reduce_mean(tf.where(y_pred < y_true, 2 * (y_true - y_pred), y_pred - y_true)) uses tf.where to multiply the error by 2 when y_pred < y_true, increasing penalty for under-predictions. Options B and C treat errors symmetrically. def custom_loss(y_true, y_pred): return tf.reduce_sum(y_pred - y_true) sums signed differences, which is incorrect.

3. Final Answer:

   def custom_loss(y_true, y_pred): return tf.reduce_mean(tf.where(y_pred < y_true, 2 * (y_true - y_pred), y_pred - y_true)) -> Option A

4. Quick Check:

   Conditional penalty for under-prediction = def custom_loss(y_true, y_pred): return tf.reduce_mean(tf.where(y_pred < y_true, 2 * (y_true - y_pred), y_pred - y_true)) [OK]

Hint: Use tf.where to weight errors differently [OK]

Common Mistakes:

• Using symmetric loss ignoring under/over difference
• Summing signed differences causing wrong loss
• Not using conditional logic for penalty