US Patent Application 17725825. DEEP NEURAL NETWORKS (DNN) INFERENCE USING PRACTICAL EARLY EXIT NETWORKS simplified abstract

DEEP NEURAL NETWORKS (DNN) INFERENCE USING PRACTICAL EARLY EXIT NETWORKS

Organization Name

Microsoft Technology Licensing, LLC

Inventor(s)

Anand Padmanabha Iyer of Redmond WA (US)

Swapnil Sunilkumar Gandhi of Bengaluru (IN)

DEEP NEURAL NETWORKS (DNN) INFERENCE USING PRACTICAL EARLY EXIT NETWORKS - A simplified explanation of the abstract

• This abstract for appeared for US patent application number 17725825 Titled 'DEEP NEURAL NETWORKS (DNN) INFERENCE USING PRACTICAL EARLY EXIT NETWORKS'

Simplified Explanation

The abstract describes methods and systems for using machine learning to make inferences. These methods involve splitting a machine learning model into smaller portions based on a load forecast, determining the batch size for processing requests, and using available resources to execute the model portions and generate inferences.

Original Abstract Submitted

The present disclosure relates to methods and systems for providing inferences using machine learning systems. The methods and systems receive a load forecast for processing requests by a machine learning model and split the machine learning model into a plurality machine learning model portions based on the load forecast. The methods and systems determine a batch size for the requests for the machine learning model portions. The methods and systems use one or more available resources to execute the plurality of machine learning model portions to process the requests and generate inferences for the requests.