Methods of processing and generating image data in a connectionist network

A vehicle comprising:

• at least one image sensor with multiple channels for acquiring an image comprising a plurality of input picture elements, the image sensor being a red-clear-clear-clear sensor, the plurality of input picture elements comprising a first portion and at least a second portion of input picture elements, wherein the first portion of input picture elements represents a first channel of the image sensor and the at least second portion of input picture elements represents a second channel of the image sensor, the first portion and the at least second portion of input picture elements consisting of an unequal number of picture elements;
• and
• a non-transitory storage device comprising instructions that, when executed by a processor, cause the processor to classify traffic signs, the non-transitory storage device comprising a neural network that comprises a plurality of units, each unit having a data input, a data output, and at least one processing parameter, wherein processing of input data by means of a respective one of the plurality of units is at least partially determined by the at least one processing parameter of the respective unit, the processor implements a multi-channel unit forming a respective one of the plurality of units, the multi-channel unit forming a first unit of the neural network, the processor configured to:
• receive, at the data input, the plurality of input picture elements;
• process the first portion and the at least second portion of input picture elements separately from each other;
• and
• output, at the data output, the processed first portion and at least second portion of input picture elements, the processed first portion and at least second portion of input picture elements consisting of an equal number of picture elements, the processed first portion and at least second portion of input picture elements being further processed by at least one subsequent unit of the neural network and data output by a last unit of the neural network comprising a discrete variable classifying the image represented by the plurality of input picture elements received by the first unit.