首页>
外国专利>
Self-learning network of neural network models for safety-relevant applications in the vehicle for the detection and classification of objects in the vicinity of the vehicle with the help of a deep learning process
Self-learning network of neural network models for safety-relevant applications in the vehicle for the detection and classification of objects in the vicinity of the vehicle with the help of a deep learning process
The invention relates to a self-learning system and / or measuring system comprising a computer system with a network of neural network models (16, 136, 138) of this computer system, referred to below as a neural network. The neural network models of the computer system represent the nodes of the neural network. The neural network has at least a first neural network model (16) of the computer system with a first set of parameters and a second neural network model (136) of the computer system with a second set of parameters and a third neural network model (138 ) of the computer system with a third set of parameters. A first parameter modification device (140) for the first neural network model (16) and a second parameter modification device (141) for the second neural network model (136) are part of the device. Each neural network model of the neural network has at least a first input data stream and a first output data stream. The third neural network model (138) has a second input data stream. The output data stream of the first neural network model (16) is the first input data stream of the third neural network model (138) and the output data stream of the second neural network model (136) is the second input data stream of the third neural network model (138). The output data stream of the third neural network (138) depends at least on its first and second input data stream. An output data stream of the third neural network (138) can change the parameter sets of the first and / or second neural network (16, 136) by means of the first or second parameter modification device (140, 141).
展开▼
