What Machine Learning Cannot (Yet) Do? It's tremendously important in this era of frenzied speculation about AI to understand what the limitations of machine learning are. First, and foremost, it is important to realize that ML is not omnipotent. As far as we know, from research over the past 50 years, we have come to realize that ML is a mode of knowledge acquisition without explicit programming that has some definite boundaries. Just like computation as a process has inherent limitations — for example, it is not possible now, nor will it ever be possible in the future, to decide if an arbitrary program will halt — ML also has intrinsic limitations that cannot be overcome by throwing more GPU machines at the problem, or using faster computers. I know this news might come as a disappointment to many fans of ML, but it is important to know that ML is not the salvation to all our problems. There are other ways to acquire information, and people incidentally use these all the tim...
Posts
- Get link
- X
- Other Apps
How to acquire a good mathematical background to do machine learning? Machine learning requires a strong background in math, if you want to follow the recent research, and especially if you want to be able to invent new techniques. The background preparation initially can be modest -- a smattering of basic calculus, linear algebra, and statistics should get you going -- but in the long run, you will have to devote serious time to becoming fluent in the core mathematical topics used in the field today. Here is a list of math textbooks that I have personally found useful. It is, as with all such lists, a somewhat idiosyncratic list, but each of the books on this list is a well-known classic in the field. Happy reading! Linear Algebra by Strang. He writes math like few folks do, no endless paragraphs of definitions and theorems. He tells you why something is important. He wears his heart on his sleeve. If you want to spend a lifetime doing ML, sleep with this book under...