Abstract Methods for artificial neural networks 5 A method for an artificial neural network is provided. The method comprises providing the artificial neural network, wherein the artificial neural network is trained to reduce the confidence of the artificial neural network in classifying inputs outside a desirable input distribution is provided by training the artificial neural network (230) using a first set of inputs and associated labels, the labels correctly classifying the corresponding inputs, 10 wherein the inputs within the first set are within the desirable input distribution of the artificial neural network; training the artificial neural network using a second set of inputs and associated labels, wherein the inputs within the second set are outside of the desirable input distribution of the artificial neural network, and wherein the labels within the second set comprise randomly assigned classifications; and feeding one or more 15 inputs through the artificial neural network to determine classifications, classifying the inputs, and confidence values associated with the classifications. [Fig 3] Fig. 3 0 + Fig. 4 402 Train ANN using first set of inputs and labels Train ANN using 404 second set of inputs and labels
Methods for artificial neural networks
2021-07-22
Patent
Electronic Resource
English
IPC: | G06V / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06T Bilddatenverarbeitung oder Bilddatenerzeugung allgemein , IMAGE DATA PROCESSING OR GENERATION, IN GENERAL / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
AIAA | 2015
|AIAA | 2006
|Generalized Adaptive Artificial Neural Networks
NTRS | 1993
|Artificial road load generation using artificial neural networks
Automotive engineering | 2015
|