Evaluation & Calculate Top-N Accuracy: Top 1 and Top 5

Question

I have come across a few (Machine learning-classification problem) journal papers mentioned evaluate the accuracy with the Top-N approach. Data was show that Top 1 accuracy = 42.5%, and Top-5 accuracy = 72.5% in the same training, testing condition. I wonder how to calculate this percentage of top-1 and top-5?

Can someone show me an example and steps to calculate this?

Thanks

Answer 1

I’d try to answer in the simplest way that I can.

Top-1 accuracy is the conventional accuracy, which means that the model answer (the one with the highest probability) must be exactly the expected answer.

Top-5 accuracy means that any of your model that gives 5 highest probability answers that must match the expected answer.

Let's say you're applying a machine learning algorithm for object recognition using a neural network. A picture of a cat is shown, and these are the outputs of your neural network:

• Tiger: 0.4

• Dog: 0.3

• Cat: 0.1

• Lynx: 0.09

• Lion: 0.08

• Bird: 0.02

• Bear: 0.01

In the above-mentioned probabilities:

Using top-1 accuracy, you will count this output as wrong, because it predicted a tiger.

Using top-5 accuracy, you count this output as correct, because the cat is among the top-5 guesses.

I hope this explanation would help you to understand.

If you want to know the real-world applications of Machine Learning then you can go through this video:

To Learn the application of machine learning, and types of machine learning go through this machine learning tutorial.

Comments

It worked for me!

---

well explained!

---

Thanks for the easy to understand explanation.

---

Thanks a lot for this answer. According to you, is Top-5 really a good metric, or is it just a way to exaggerate the true capabilities of a neural network?

---

Thanks for this clear demonstration.

---

I think the top-5 metric is pretty useful because a picture can have more details than one object.

---

top-5 accuracy will always be higher than Top-1 accuracy

---

Thanks for a nice explanation

---

Pretty good explaination.

Answer 2

The complement of the accuracy is the error:

The top-1 error:- The percentage of time that the classifier did not give the correct class the highest probability score.
The top-5 error:- The percentage of time that the classifier did not involve the correct class among the top 5 probabilities or guesses.

Comments

Nice explanation..taking error instead of accuracy really puts things into perspective!

---

Thanks for this explanation. Which is easy to understand the answer.