Why Loss functions (MSELoss, CrossEntropyLoss) in PyTorch? - Purpose & Use Cases

The Big Idea

What if your machine could learn from its mistakes just like you do, without you telling it every time?

The Scenario

Imagine you are trying to teach a robot to recognize fruits by looking at pictures. You write down rules yourself to guess if a fruit is an apple or an orange based on color and shape. But every time the robot guesses wrong, you have to check and fix the rules manually.

The Problem

This manual checking is slow and tiring. You might miss some mistakes or make wrong fixes. The robot never really learns from its errors on its own, so it keeps making the same mistakes again and again.

The Solution

Loss functions like MSELoss and CrossEntropyLoss help the robot understand how wrong its guesses are. They give a clear number showing the error. The robot uses this number to adjust itself automatically, improving step by step without needing you to fix rules manually.

Before vs After

✗ Before

if guess != correct_label:
    fix_rules_manually()

✓ After

loss = loss_function(predictions, targets)
loss.backward()
optimizer.step()
optimizer.zero_grad()

What It Enables

Loss functions enable machines to learn from their mistakes automatically and improve their predictions over time.

Real Life Example

When you use a voice assistant, loss functions help it learn to understand your speech better by measuring how far its guesses are from what you actually said and improving itself continuously.

Key Takeaways

Manual error checking is slow and unreliable.

Loss functions provide a clear measure of prediction errors.

They allow automatic learning and improvement in models.

Practice

1. Which loss function in PyTorch is best suited for predicting continuous values like house prices?

easy

A. torch.nn.MSELoss

B. torch.nn.CrossEntropyLoss

C. torch.nn.BCELoss

D. torch.nn.NLLLoss

Solution

1. Step 1: Understand the type of prediction

   Predicting house prices is a regression problem where output is continuous.

2. Step 2: Match loss function to problem type

   MSELoss calculates mean squared error, ideal for continuous outputs. CrossEntropyLoss is for classification, not regression.

3. Final Answer:

   torch.nn.MSELoss -> Option A

4. Quick Check:

   Regression uses MSELoss = C [OK]

Hint: Use MSELoss for continuous outputs, CrossEntropyLoss for classes [OK]

Common Mistakes:

• Choosing CrossEntropyLoss for regression tasks
• Confusing BCELoss with MSELoss
• Using NLLLoss without log probabilities

2. Which of the following is the correct way to create a CrossEntropyLoss object in PyTorch?

easy

A. loss = torch.nn.CrossEntropy()

B. loss = torch.nn.MSELoss()

C. loss = torch.nn.CrossEntropyLoss()

D. loss = torch.CrossEntropyLoss()

Solution

1. Step 1: Recall PyTorch loss function syntax

   Loss functions are in torch.nn and instantiated with parentheses.

2. Step 2: Identify correct class name and module

   CrossEntropyLoss is the correct class name under torch.nn. Options A misses 'Loss' and C misses 'nn'.

3. Final Answer:

   loss = torch.nn.CrossEntropyLoss() -> Option C

4. Quick Check:

   Correct class and module = D [OK]

Hint: Use torch.nn.CrossEntropyLoss() exactly for classification loss [OK]

Common Mistakes:

• Missing parentheses when creating loss object
• Using torch.CrossEntropyLoss() instead of torch.nn.CrossEntropyLoss()
• Confusing MSELoss with CrossEntropyLoss

3. What will be the output loss value when using torch.nn.MSELoss on predictions tensor([2.0, 3.0]) and targets tensor([1.0, 5.0])?

medium

A. 2.5

B. 3.0

C. 1.5

D. 4.0

Solution

1. Step 1: Calculate squared differences

   Differences: (2.0-1.0)=1.0, (3.0-5.0)=-2.0; squared: 1.0, 4.0

2. Step 2: Compute mean of squared differences

   Mean = (1.0 + 4.0) / 2 = 2.5

3. Final Answer:

   2.5 -> Option A

4. Quick Check:

   MSE = mean squared error = 2.5 [OK]

Hint: Square errors, then average for MSELoss output [OK]

Common Mistakes:

• Forgetting to square the differences
• Summing without averaging
• Mixing up prediction and target order

4. Given this code snippet, what is the error?

import torch
loss_fn = torch.nn.CrossEntropyLoss()
pred = torch.tensor([[0.2, 0.8], [0.6, 0.4]])
target = torch.tensor([1, 0])
loss = loss_fn(pred, target)
print(loss.item())

medium

A. Loss function should be MSELoss for this target

B. Target tensor should be one-hot encoded

C. No error, code runs correctly

D. Predictions should be raw scores (logits), not probabilities

Solution

1. Step 1: Check input requirements for CrossEntropyLoss

   CrossEntropyLoss expects raw scores (logits), not probabilities.

2. Step 2: Analyze given predictions

   Predictions are probabilities (sum to 1), so applying CrossEntropyLoss directly causes incorrect loss calculation.

3. Final Answer:

   Predictions should be raw scores (logits), not probabilities -> Option D

4. Quick Check:

   CrossEntropyLoss needs logits = A [OK]

Hint: Use logits, not probabilities, with CrossEntropyLoss [OK]

Common Mistakes:

• Passing probabilities instead of logits to CrossEntropyLoss
• Using one-hot targets instead of class indices
• Confusing MSELoss with CrossEntropyLoss for classification

5. You have a multi-class classification problem with 4 classes. Your model outputs raw scores (logits) of shape (batch_size, 4). Which loss function and target format should you use in PyTorch?

hard

A. Use torch.nn.MSELoss with target as one-hot vectors

B. Use torch.nn.CrossEntropyLoss with target as class indices (0 to 3)

C. Use torch.nn.BCELoss with target as class indices

D. Use torch.nn.CrossEntropyLoss with target as one-hot vectors

Solution

1. Step 1: Identify loss function for multi-class classification

   CrossEntropyLoss is designed for multi-class classification with logits.

2. Step 2: Determine correct target format

   CrossEntropyLoss expects target as class indices (integers), not one-hot vectors.

3. Final Answer:

   Use torch.nn.CrossEntropyLoss with target as class indices (0 to 3) -> Option B

4. Quick Check:

   CrossEntropyLoss + class indices = B [OK]

Hint: CrossEntropyLoss needs logits and integer class labels [OK]

Common Mistakes:

• Passing one-hot vectors as targets to CrossEntropyLoss
• Using MSELoss for classification
• Using BCELoss for multi-class without sigmoid