In this chapter, we stepped out of our comfort zone when we built a music-genre classifier. Not having a deep understanding of music theory, at first we failed to train a classifier that predicts the music genre of songs with reasonable accuracy using FFT. But, then, we created a classifier that showed really usable performance using MFC features.

In both cases, we used features that we understood only enough to know how and where to put them in our classifier setup. The first one failed, and the second succeeded. The difference between them is that in the second case, we relied on features that were created by experts in the field.

And that is totally OK. If we are mainly interested in the result, we sometimes simply have to take shortcuts–we just have to make sure that these shortcuts are from domain-specific experts. And because we've learned how to correctly measure performance in this new multi-class classification problem, we took these shortcuts with confidence.

In Chapter 12, Computer Vision, will take a look at image processing, feature representations, CNN, and GAN.