Artificial intelligence (AI) systems can be fooled by certain image inputs. Called adversarial examples, they incorporate ...

CIFAR-10 problems analyze crude 32 x 32 color images to predict which of 10 classes the image is. Here, Dr. James McCaffrey of Microsoft Research shows how to create a PyTorch image classification ...

Suppose you have a collection of digital photos you took on a trip to a zoo. You want to programmatically classify each photo as one of the 100 different kinds of animals you photographed: "aardvark," ...

When something does zero-shot image classification, that means it’s able to make judgments about the contents of an image without the user needing to train the system beforehand on what to look for.

Welcome to TNW’s beginner’s guide to AI. This (currently) four part feature should provide you with a very basic understanding of what AI is, what it can do, and how it works. The guide contains ...

In machine learning, understanding why a model makes certain decisions is often just as important as whether those decisions are correct. For instance, a machine-learning model might correctly predict ...