0
$\begingroup$

Let's consider I have 1000 unlabeled data points. Out of these 1000 points, I manually labeled 200. Now, I am feeling lazy and don't want to label manually the remaining 800 data points.

What would be the next step? I am considering using dimension reduction techniques, such as PCA, to visually assess if the dimension reduction accurately separates the labeled data. If it does, I plan to utilize the reduced dimensions and classify the remaining 800 unlabeled data points using a random classifier, for example, KNN.

Does this align with the concept of semi-supervised learning, or am I missing something? Is it necessary to visually inspect the data points to evaluate the performance of dimension reduction and automated labeling?

enter image description here

enter image description here

source of images: https://www.kaggle.com/code/shivamb/semi-supervised-classification-using-autoencoders

$\endgroup$

0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.