concept classification in category Keras

appears as: classification, classification, classifications
Probabilistic Deep Learning: With Python, Keras and TensorFlow Probability

This is an excerpt from Manning's book Probabilistic Deep Learning: With Python, Keras and TensorFlow Probability.

Already this simple example makes clear that feature engineering, meaning defining and extracting those properties from the image that are important for the classification, is a complicated and time-consuming task, which usually requires a high level of expertise. The (slow) progress in computer vision was mainly driven by the construction of new and better features.

Concerning classification, you have used a loss function called categorical cross entropy (see section 2.1). What is categorical cross entropy and how do you get to it in the first place? You probably can guess by which approach you can derive this loss function. It turns out that the likelihood function is your friend which will yield the cross entropy as appropriate loss function in classification tasks.