US Patent Application 18249389. Machine-Learned Discretization Level Reduction simplified abstract

From WikiPatents
Jump to navigation Jump to search

Machine-Learned Discretization Level Reduction

Organization Name

GOOGLE LLC

Inventor(s)

Shumeet Baluja of Leesburgh VA (US)

Machine-Learned Discretization Level Reduction - A simplified explanation of the abstract

This abstract first appeared for US patent application 18249389 titled 'Machine-Learned Discretization Level Reduction

Simplified Explanation

- The patent application describes a computer-implemented method for improving the representation of information in tensor data. - The method involves obtaining input tensor data and providing it to a machine-learned model for level reduction. - The model is trained using reconstructed input tensor data generated using its own output. - The model includes one or more level reduction layers that reduce the number of discretization levels in the input data. - The goal is to provide level-reduced tensor data with improved representation of information.


Original Abstract Submitted

A computer-implemented method for providing level-reduced tensor data having improved representation of information can include obtaining input tensor data, providing the input tensor data as input to a machine-learned discretization level reduction model configured to receive tensor data having a number of discretization levels and produce, in response to receiving the tensor data, level-reduced tensor data having a reduced number of discretization levels, and obtaining, from the machine-learned discretization level reduction model, the level-reduced tensor data. The machine-learned discretization level reduction model is trained using reconstructed input tensor data generated using an output of the machine-learned discretization level reduction model. The machine-learned discretization level reduction model can include one or more level reduction layers configured to receive input having a first number of discretization levels and to provide a layer output having a reduced a number of discretization levels.