Restoring balance in machine learning datasets

phys.org | 10/11/2018 | Staff
finter (Posted by) Level 4


If you want to teach a child what an elephant looks like, you have an infinite number of options. Take a photo from National Geographic, a stuffed animal of Dumbo, or an elephant keychain; show it to the child; and the next time he sees an object which looks like an elephant he will likely point and say the word.

Teaching AI what an elephant looks like is a bit different. To train a machine learning algorithm, you will likely need thousands of elephant images using different perspectives, such as head, tail, and profile. But then, even after ingesting thousands of photos, if you connect your algorithm to a camera and show it a pink elephant keychain, it likely won't recognize it as an elephant.

Form - Data - Bias - Accuracy - Learning

This is a form of data bias, and it often negatively affects the accuracy of deep learning classifiers. To fix this bias, using the same example, we would need at least 50-100 images of pink elephants, which could be problematic since...
(Excerpt) Read more at: phys.org
Wake Up To Breaking News!
I find it extremely funny when people keep voting and expecting the government to change!
Sign In or Register to comment.

Welcome to Long Room!

Where The World Finds Its News!