On the exercises and problems
It's not uncommon-technical books to include a admonition from the author so readers must do the exercises and prob Lems. I always feel a little peculiar when I read such warnings. Would something bad happen to me if I don ' t do the exercises and problems? Of course not. I ' ll gain some time, but at the expense of depth of understanding. Sometimes that ' s worth it. Sometimes it ' s not.
So what's worth doing in the this book? My advice is so you really should attempt most of the exercises, and you should aim does most of the PROBL Ems.
You should does most of the exercises because they ' re basic checks so you ' ve understood the material. If you can ' t solve a exercise relatively easily, you ' ve probably missed something fundamental. Of course, if you do get stuck in an occasional exercise, just move on-chances is it ' s just a small misunderstanding on Your part, or maybe I ' ve worded something poorly. If most exercises is a struggle, then you probably need to reread some earlier material.
The problems is another matter. They ' re more difficult than the exercises, and you'll likely struggle to solve some problems. That's annoying, but, of course, patience in the face of such frustration are the only-to truly understand and internal Ize a subject.
With this said, I don ' t recommend working through all the problems. What ' s even better are to find your own project. Maybe want to use neural nets to classify your music collection. Or to predict stock prices. Or whatever. But find a project, about. Then you can ignore the problems in the book, or use them simply as inspiration for work on your own project. Struggling with a project, about would teach you, than working through any number of set problems. Emotional commitment is a key to achieving mastery.
Of course, you are not having such a project in mind, at least up front. That ' s fine. Work through those problems-feel motivated to work on. and use the "material in the" to "help" search for ideas for creative personal projects.
Neural Networks and Deep learning_#2