There are methods called "scoring systems" where you give a image scores such as "0.9 stripes, 0.0 red, 0.8 hair, ..." and use those scores to classify objects. It's an older idea, not used to determine if the network is learning. It's not in a standard CNN. To determine if relevant information is being learned or not, it's standard to use the testing accuracy, training accuracy, confusion matrix, or AUC. Determining what exactly a CNN is learning is a complicated search problem that's ongoing. In short - you can't really know. For a basic network, you can tell that is learning *something* but not what it's actually using to make determinations.