Parametric machines: a fresh approach to architecture search

07/06/2020
by   Pietro Vertechi, et al.
0

Using tools from category theory, we provide a framework where artificial neural networks, and their architectures, can be formally described. We first define the notion of machine in a general categorical context, and show how simple machines can be combined into more complex ones. We explore finite- and infinite-depth machines, which generalize neural networks and neural ordinary differential equations. Borrowing ideas from functional analysis and kernel methods, we build complete, normed, infinite-dimensional spaces of machines, and discuss how to find optimal architectures and parameters – within those spaces – to solve a given computational problem. In our numerical experiments, these kernel-inspired networks can outperform classical neural networks when the training dataset is small.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset