Activation functions (ReLU, Sigmoid, Softmax) in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the purpose of an activation function in a neural network?

An activation function adds non-linearity to the model, allowing it to learn complex patterns and make decisions beyond simple linear relationships.

beginner

Describe the ReLU activation function and its output behavior.

ReLU (Rectified Linear Unit) outputs the input directly if it is positive; otherwise, it outputs zero. It helps models learn faster and reduces the chance of vanishing gradients.

beginner

What is the range of the Sigmoid activation function and why is it useful?

Sigmoid outputs values between 0 and 1, making it useful for models that predict probabilities or binary outcomes.

intermediate

Explain the Softmax activation function and when it is typically used.

Softmax converts a vector of numbers into probabilities that sum to 1. It is commonly used in the output layer for multi-class classification problems.

intermediate

What problem does ReLU help to solve compared to Sigmoid or Tanh?

ReLU helps reduce the vanishing gradient problem by allowing gradients to flow when inputs are positive, unlike Sigmoid or Tanh which can squash gradients to near zero.

Which activation function outputs values strictly between 0 and 1?

A Softmax

B ReLU

C Linear

D Sigmoid

Sigmoid outputs values between 0 and 1, making it suitable for probability predictions.

What does the ReLU function output when the input is negative?

A The input value

B Negative of the input

C Zero

D One

ReLU outputs zero for any negative input.

Softmax is mainly used in which part of a neural network?

A Output layer for multi-class classification

B Hidden layers

C Input layer

D Output layer for regression

Softmax converts outputs into probabilities for multi-class classification in the output layer.

Which activation function can cause the vanishing gradient problem?

A Sigmoid

B ReLU

C Softmax

D Leaky ReLU

Sigmoid can squash gradients to near zero, causing vanishing gradients.

What is a key benefit of using ReLU over Sigmoid?

A Outputs probabilities

B Non-linear but faster to compute and reduces vanishing gradients

C Always outputs positive values

D Used for multi-class classification

ReLU is simple, fast, and helps reduce vanishing gradients compared to Sigmoid.

Explain how ReLU, Sigmoid, and Softmax activation functions differ in their output and typical use cases.

Think about the output range and where in the network each is used.

Describe why activation functions are important in neural networks and what would happen without them.

Consider what linear vs non-linear means for learning.

Practice

1. Which activation function is best suited for the output layer of a binary classification model in PyTorch?

easy

A. Sigmoid

B. ReLU

C. Softmax

D. Tanh

Solution

1. Step 1: Understand the output requirements for binary classification

   Binary classification outputs a probability between 0 and 1 for one class, so the activation must squash values into this range.

2. Step 2: Match activation functions to output needs

   Sigmoid outputs values between 0 and 1, making it ideal for binary classification outputs. ReLU outputs zero or positive values without upper bound, Softmax is for multi-class, and Tanh outputs between -1 and 1.

3. Final Answer:

   Sigmoid -> Option A

4. Quick Check:

   Binary output needs probability = Sigmoid [OK]

Hint: Binary output? Use Sigmoid for probability between 0 and 1 [OK]

Common Mistakes:

• Choosing ReLU which doesn't limit output to 0-1
• Using Softmax for binary instead of multi-class
• Confusing Tanh with Sigmoid output range

2. Which of the following is the correct way to apply the ReLU activation function to a tensor x in PyTorch?

easy

A. torch.activation.relu(x)

B. torch.nn.functional.relu(x)

C. torch.nn.ReLU(x)

D. torch.relu(x)

Solution

1. Step 1: Recall PyTorch ReLU usage

   ReLU can be applied using the functional API or as a module. The functional API call is torch.nn.functional.relu(x).

2. Step 2: Check each option

   torch.relu(x) is incorrect because torch.relu does not exist. torch.activation.relu(x) is invalid syntax. torch.nn.ReLU(x) tries to call the module directly without instantiation. torch.nn.functional.relu(x) correctly uses the functional API.

3. Final Answer:

   torch.nn.functional.relu(x) -> Option B

4. Quick Check:

   Use functional API for ReLU = torch.nn.functional.relu(x) [OK]

Hint: Use torch.nn.functional.relu(x) for direct ReLU call [OK]

Common Mistakes:

• Trying to call torch.relu which doesn't exist
• Using torch.nn.ReLU without creating an instance
• Confusing module and functional API usage

3. What is the output of the following PyTorch code?

import torch
import torch.nn.functional as F
x = torch.tensor([-1.0, 0.0, 2.0])
output = F.relu(x)
print(output.tolist())

medium

A. [-1.0, 0.0, 2.0]

B. [0.0, 1.0, 1.0]

C. [0.0, 0.0, 2.0]

D. [-1.0, 0.0, 0.0]

Solution

1. Step 1: Understand ReLU behavior on input tensor

   ReLU sets negative values to zero and keeps positive values unchanged.

2. Step 2: Apply ReLU to each element

   -1.0 becomes 0.0, 0.0 stays 0.0, 2.0 stays 2.0. So output is [0.0, 0.0, 2.0].

3. Final Answer:

   [0.0, 0.0, 2.0] -> Option C

4. Quick Check:

   ReLU zeroes negatives = [0.0, 0.0, 2.0] [OK]

Hint: ReLU zeroes negatives, keeps positives same [OK]

Common Mistakes:

• Leaving negative values unchanged
• Confusing ReLU with Sigmoid output
• Assuming ReLU changes zeros to ones

4. The following code aims to apply Softmax to a tensor x along dimension 1 but throws an error. What is the error and how to fix it?

import torch
import torch.nn.functional as F
x = torch.tensor([[1.0, 2.0, 3.0], [1.0, 2.0, 3.0]])
output = F.softmax(x, dim=2)
print(output)

medium

A. Missing activation import; fix by importing torch.nn

B. Softmax requires 1D tensor; fix by flattening x

C. Softmax cannot be applied to float tensors; convert to int

D. Dimension 2 is out of range for tensor of shape (2,3); fix by using dim=1

Solution

1. Step 1: Check tensor shape and dimension argument

   Tensor x has shape (2, 3), so valid dims are 0 and 1. Using dim=2 is invalid and causes an error.

2. Step 2: Correct the dimension argument

   To apply Softmax across columns (features), use dim=1. This fixes the error.

3. Final Answer:

   Dimension 2 is out of range for tensor of shape (2,3); fix by using dim=1 -> Option D

4. Quick Check:

   Tensor shape (2,3) means max dim=1 [OK]

Hint: Check tensor shape before choosing dim for Softmax [OK]

Common Mistakes:

• Using invalid dimension index for Softmax
• Thinking Softmax needs 1D input only
• Ignoring error message about dimension out of range

5. You have a multi-class classification problem with 4 classes. Which activation function should you use in the output layer and why?

Choose the best option.

hard

A. Softmax, because it outputs probabilities that sum to 1 across all classes

B. Sigmoid, because it outputs probabilities for each class independently

C. Tanh, because it outputs values between -1 and 1 for better gradients

D. ReLU, because it outputs positive values for all classes

Solution

1. Step 1: Understand multi-class output requirements

   For multi-class classification, the output layer should produce probabilities for each class that sum to 1, representing a valid probability distribution.

2. Step 2: Match activation functions to multi-class needs

   Softmax converts raw scores into probabilities that sum to 1 across classes. ReLU does not produce probabilities, Sigmoid treats classes independently (not summing to 1), and Tanh outputs values between -1 and 1, not probabilities.

3. Final Answer:

   Softmax, because it outputs probabilities that sum to 1 across all classes -> Option A

4. Quick Check:

   Multi-class needs sum-to-1 probabilities = Softmax [OK]

Hint: Multi-class output? Use Softmax for normalized probabilities [OK]

Common Mistakes:

• Using Sigmoid which treats classes independently
• Choosing ReLU which is not probabilistic
• Confusing Tanh output range with probabilities