Why can’t there be a discussion on machine learning without everyone on HN trying to prove how unnecessary it is. Queue the anecdotes on simpler regression based methods, over paid scientists, and how much superior some other simpler method is.
I normally do not feel the need to comment about deep learning, because it is only tangentially related to some of my past projects, but I can also understand those who might want to comment negatively, because I have seen many cases of managers who did not understand at all how exactly certain problems can be solved, but nevertheless they pushed vigorously for the use of deep learning to replace other better suited solutions, because they believed it to be a modern and universally better method.
So there were times when I was tired of seeing one more attempt to misuse deep learning and to have to explain and demonstrate once more which solution is better.
Obviously, any such opinions, about which method is better in a certain case, should be proved with numerical results from tests or simulations, not with guesses, but some times that requires a lot of work to implement both methods, even if you are pretty sure about which will be the result.
For instance, FP vs Imperative, where a simple example (map for instance) is being shown and someone always compares it to a for loop, and then disses garbage collection. They're obviously thinking of their existing language (we know from the GC comment) and not of whatever point the OP is trying to make about composability or whatever.
To some degree, examples are to blame. They often aren't good and don't show, to the actual audience, what the author intended. In my FP example, you need something that can't get stuck in a syntax-level debate and is complex enough for the benefits to show through. Like doing something that would take a 50-level deep stack of for loops in an unnested fashion.
It gives you more respect for great teachers who can pull examples out of the air that both illustrate and refuse to misdirect.
Can you (because I certainly can't) write a good post or blog about the minimum useful deep learning project that can't be done equivalently via any other methods?
And the mistake people make is that they don't start with a simple model. They move straight into the heavy ones.