Activation functions in ML Python - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to apply the ReLU activation function to the input tensor.

ML Python

import torch
input_tensor = torch.tensor([-1.0, 0.0, 2.0, -3.0])
output = torch.nn.functional.[1](input_tensor)

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

Atanh

Bsigmoid

Csoftmax

Drelu

Attempts:

3 left

💡 Hint

Common Mistakes

Using sigmoid instead of relu changes output range.

Using softmax applies normalization, not element-wise activation.

The ReLU function replaces negative values with zero, keeping positive values unchanged.

2fill in blank

medium

Complete the code to apply the sigmoid activation function to the input tensor.

ML Python

import torch
input_tensor = torch.tensor([-2.0, 0.0, 2.0])
output = torch.nn.functional.[1](input_tensor)

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

Asigmoid

Brelu

Csoftmax

Dtanh

Attempts:

3 left

💡 Hint

Common Mistakes

Using relu instead of sigmoid changes output range.

Using softmax applies normalization across vector, not element-wise.

The sigmoid function outputs values between 0 and 1, useful for probabilities.

3fill in blank

hard

Fix the error in the code by choosing the correct activation function to apply softmax over dimension 1.

ML Python

import torch
input_tensor = torch.tensor([[1.0, 2.0, 3.0], [1.0, 2.0, 3.0]])
output = torch.nn.functional.[1](input_tensor, dim=1)

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

Asigmoid

Bsoftmax

Crelu

Dtanh

Attempts:

3 left

💡 Hint

Common Mistakes

Using relu or sigmoid does not normalize across dimension.

Forgetting to specify dim parameter causes errors.

Softmax converts logits to probabilities across the specified dimension.

4fill in blank

hard

Fill both blanks to define a custom activation function that applies tanh and then scales the output by 2.

ML Python

import torch
input_tensor = torch.tensor([-1.0, 0.0, 1.0])
output = 2 * torch.nn.functional.[1](input_tensor) [2] 0

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

Atanh

B+

C-

D*

Attempts:

3 left

💡 Hint

Common Mistakes

Using relu instead of tanh changes output range.

Using multiplication instead of addition after scaling.

The tanh function outputs between -1 and 1. Adding 0 keeps the output unchanged after scaling.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps each word to its sigmoid activation applied to its length.

ML Python

import torch
words = ['hi', 'hello', 'hey']
result = {word: torch.nn.functional.[1](torch.tensor(len(word))) for word in words if len(word) [2] 2 and len(word) [3] 5}

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

Asigmoid

B>

C<

D==

Attempts:

3 left

💡 Hint

Common Mistakes

Using relu instead of sigmoid changes output range.

Using equality instead of range conditions.

This comprehension applies sigmoid to the length of words longer than 2 and less than 5 characters.