Formulate the problem
If you can solve your problem without machine learning, don't use it. If the task can be solved with traditional programming techniques, congratulations! You don't need machine learning! Furthermore if your problem is of the kind where you can't allow errors, do not use machine learning.
For the start of your machine learning project, it is necessary to reduce a real-world problem to a machine learning task. Machine learning algorithms were developed by mathematicians and mostly tested on neat data in a controlled environment. You are fine if you can define your problem in terms of some existing machine learning approach: classification, regression, clustering, and so on. But to date, there are many problems that can't ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access