Yes. The distribution of information is indeed a complex problem, as graph theory shows us.
Regarding science is about one standard deviation further than software development in complexity. It's not necessarily a trade off. On the contrary, software applies scientific breakthroughs.
My problem isn't the graph or even its particular failings (vanishing gradients in science being one of many), it's the ideological opposition to regularization.
Regarding science is about one standard deviation further than software development in complexity. It's not necessarily a trade off. On the contrary, software applies scientific breakthroughs.