Jason W Mcghee

US Patent:

20210287089, Sep 16, 2021

Filed:

Mar 11, 2021

Appl. No.:

17/198841

Inventors:

- Boston MA, US
Jason McGhee - Walnut Creek CA, US
Jesse Bannon - Port Orchard WA, US
Joshua Matthew Weiner - Arvada CO, US

International Classification:

G06N 3/08
G06F 17/18
G06N 3/04

Abstract:

Systems and methods are described for developing and using neural network models. An example method of training a neural network includes: oscillating a learning rate while performing a preliminary training of a neural network; determining, based on the preliminary training, a number of training epochs to perform for a subsequent training session; and training the neural network using the determined number of training epochs. The systems and methods can be used to build neural network models that efficiently and accurately handle heterogeneous data.