[link]
Summary by senior author [duvenaud on hackernews](https://news.ycombinator.com/item?id=18678078). A few years ago, everyone switched their deep nets to "residual nets". Instead of building deep models like this: h1 = f1(x) h2 = f2(h1) h3 = f3(h2) h4 = f3(h3) y = f5(h4) They now build them like this: h1 = f1(x) + x h2 = f2(h1) + h1 h3 = f3(h2) + h2 h4 = f4(h3) + h3 y = f5(h4) + h4 Where f1, f2, etc are neural net layers. The idea is that it's easier to model a small change to an almostcorrect answer than to output the whole improved answer at once. In the last couple of years a few different groups noticed that this looks like a primitive ODE solver (Euler's method) that solves the trajectory of a system by just taking small steps in the direction of the system dynamics and adding them up. They used this connection to propose things like better training methods. We just took this idea to its logical extreme: What if we _define_ a deep net as a continuously evolving system? So instead of updating the hidden units layer by layer, we define their derivative with respect to depth instead. We call this an ODE net. Now, we can use offtheshelf adaptive ODE solvers to compute the final state of these dynamics, and call that the output of the neural network. This has drawbacks (it's slower to train) but lots of advantages too: We can loosen the numerical tolerance of the solver to make our nets faster at test time. We can also handle continuoustime models a lot more naturally. It turns out that there is also a simpler version of the change of variables formula (for density modeling) when you move to continuous time.
Your comment:
