Patent · US Active

Noisy neural network layers with noise parameters

US10839293B2 · kind B2 · utility

0Cited by
1References
22Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 12, 2019
Grant dateNov 17, 2020
Priority date
Expiry dateJun 12, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/092
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting an action to be performed by a reinforcement learning agent. The method includes obtaining an observation characterizing a current state of an environment. For each layer parameter of each noisy layer of a neural network, a respective noise value is determined. For each layer parameter of each noisy layer, a noisy current value for the layer parameter is determined from a current value of the layer parameter, a current value of a corresponding noise parameter, and the noise value. A network input including the observation is processed using the neural network in accordance with the noisy current values to generate a network output for the network input. An action is selected from a set of possible actions to be performed by the agent in response to the observation using the network output.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.