US 2026/0268648 A1 · SELF-LEARNING IN DISTRIBUTED ARCHITECTURE FOR ENHANCING ARTIFICIAL NEURAL NETWORK

Abstract

A vehicle having the first ANN model initially installed therein to generate outputs from inputs generated by one or more sensors of the vehicle. The vehicle selects an input based on an output generated from the input using the first ANN model. The vehicle has a module to incrementally train the first ANN model through unsupervised machine learning from sensor data that includes the input selected by the vehicle. Optionally, the sensor data used for the unsupervised learning may further include inputs selected by other vehicles in a population. Sensor inputs selected by vehicles are transmitted to a centralized computer server, which trains the first ANN model through supervised machine learning from sensor received inputs from the vehicles in the population and generates a second ANN model as replacement of the first ANN model previously incrementally improved via unsupervised machine learning in the population.

Claims20

Dependent claims

A system, comprising:

an artificial neural network model configured to process sensor inputs associated with operation of one or more vehicles and generate outputs;
and
a centralized server configured to:
receive one or more selected sensor inputs from the one or more vehicles;
and
transmit an updated artificial neural network model to the one or more vehicles for replacement of the artificial neural network model based at least in part on generating an updated artificial neural network model.

3 more elements

A non-transitory computer storage medium storing instructions which when executed by a computing device causes the computing device to perform a method, the method comprising:

receiving inputs from sensors installed on a vehicle;
operating vehicle controls using outputs from a first artificial neural network model;
selecting a first portion of the inputs, without selecting a second portion of the inputs, based on the outputs from the first artificial neural network model during operating of the vehicle controls using the sensors;
training, in the vehicle, the first artificial neural network model using the first portion of the inputs, without using the second portion of the inputs;
and
operating the vehicle controls using the first artificial neural network model trained using the first portion of the inputs.

3 more elements

Dependencies are inferred from the claim text.

Self-learning in distributed architecture for enhancing artificial neural network

Life of this patent

Self-learning in distributed architecture for enhancing artificial neural network

Life of this patent

Abstract

Claims20