With the basics in place, we can now move over to understand how some of the AI solutions are implemented. The blogs below can give us an idea of the kind of issues involved in solving real world problems and the typical solutions employed.
It is wise not to waste time in solving all problems right from the first principles. There are times when we must question these basics and try to think differently, but often it is wiser to start with these established best practices and see how things work.
Machine Learning experts have defined several such best practices. A lot of them may seem intuitive and trivial. Others seem to be nerdy. But, as we said, it is important to have these in mind when we start. That helps us focus on the real problem rather than the peripherals.
The foremost task is the get "good data" from the available data. Typically the data available to us is raw data collected from different sources like social media and web scraping. There is a lot more that we need to do before this data can be used for training our models. This is perhaps the most important (and tedius) component of machine learning.