NCA Group Meeting: Jules Berman presents "Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators."Closed


Hi there,

This week's NCA Group Meeting presents our CCN Intern Jules Berman, who will be speaking on the article, "Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators."


It is widely known that neural networks (NNs) are universal approximators of continuous functions. However, a less known but powerful result is that a NN with a single hidden layer can accurately approximate any nonlinear continuous operator. This universal approximation theorem of operators is suggestive of the structure and potential of deep neural networks (DNNs) in learning continuous operators or complex systems from streams of scattered data. Here, we thus extend this theorem to DNNs. We design a new network with small generalization error, the deep operator network (DeepONet), which consists of a DNN for encoding the discrete input function space (branch net) and another DNN for encoding the domain of the output functions (trunk net). We demonstrate that DeepONet can learn various explicit operators, such as integrals and fractional Laplacians, as well as implicit operators that represent deterministic and stochastic differential equations. We study different formulations of the input function space and its effect on the generalization error for 16 different diverse applications.

Flatiron Institute CCN is inviting you to a scheduled Zoom meeting.

Join from PC, Mac, Linux, iOS or Android:
    Passcode: 647196

Or Telephone:
    Dial(for higher quality, dial a number based on your current location):
        US: +1 646 558 8656 or +1 301 715 8592 or +1 312 626 6799 or +1 669 900 6833 or +1 253 215 8782 or +1 346 248 7799
    Meeting ID: 957 9476 6818
    Passcode: 647196
    International numbers available:

Or an H.323 room system: (US East)
    Meeting ID: 957 9476 6818
    Passcode: 647196

The agenda of this meeting is empty