SELF-LEARNING IN DISTRIBUTED ARCHITECTURE TO IMPROVE ARTIFICIAL NEURAL NETWORK

摘要

Vehicle with 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 for gradually training the first ANN model through unsupervised machine learning from sensor data that contain the input selected by the vehicle. Optionally, the sensor data used for unsupervised learning can further include inputs selected by other vehicles in a population. Sensor inputs selected by vehicles are transmitted to a centralized computer server that trains the first ANN model through monitored machine learning from inputs from the vehicles in the population received from the sensor, and a second ANN model to replace the first ANN model previously implemented by unsupervised machine learning gradually improved in the population.