Early Bird Registration Now Open till November 30th. Save Up to $300 Today!


DesignCon 2019 Presentation Viewer

Welcome to the DesignCon Presentation Store. Here you can view and download conference and/or show floor theater presentations before, during, and after the event. If you’re looking for a presentation from a specific session that you’re unable to find here, note that it’s likely because the presenter has not provided permission for external use or has not yet shared their presentation with us. Please check back after the event for a more complete catalogue of available presentations.

Self-Correcting Modeling Enabled by a Recurrent Neural Network

YongJin Choi (Master Technologist, Hewlett Packard Enterprise)

Sumon Dey (Senior Machine Learning Engineer, Hewlett Packard Enterprise Company)

Location: Chiphead Theater

Date: Thursday, January 31

Time: 2:50pm - 3:30pm

Track: Chiphead Theater

Session Type: Chiphead Theater (Free)

Vault Recording: TBD

Electronic component models generated by component design vendors should describe the nominal characteristics of the components, but that isn’t always the case. Environmental change, skewed components, or supply voltage variations can cause behavior of shipped components to vary. With a self-correcting model approach, component vendors generate models using the recurrent neural network format to deliver weight coefficients and number of states and hidden layers. If the model and the measurement are not correlated, end users can retrain the neural network using measured input/output.

Intended Audience