flâneur

Techniques for debugging neural networks – Non_Interactive – Software & ML

nonint.com · 681 words · saved by 1 readers

In my last post, I briefly discussed the infuriating fact that a neural network, even when deeply flawed, will often “work” in the sense that it’ll do above-random at classification or a generative network might create things that may sometimes look plausibly from the dataset. Given an idea that you’re testing out that is performing poorly – how, then, do you tell the difference between a botched implementation and an idea that just isn’t good? I think this is one of the toughest questions I have to deal with on a daily basis as an ML engineer. It’s the difference between funneling an immense amount of work into an idea that doesn’t pan out (which happens often!) or calling it early to look at something else. I definitely don’t have all the answers, but I have gathered a few tricks over the last couple of years that I wanted to share: Know how to interpret your loss curves. Different classes of NNs will have different loss curve shapes, but rarely do tweaks to a NN result in a change t

In my last post, I briefly discussed the infuriating fact that a neural network, even when deeply flawed, will often “work” in the sense that it’ll do above-random at classification or a generative network might create things that may sometimes look plausibly from the dataset. Given an idea that you’re testing out that is performing poorly – how, then, do you tell the difference between a botched implementation and an idea that just isn’t good? I think this is one of the toughest questions I have to deal with on a daily basis as an ML engineer. It’s the difference between funneling an im

related reading