▎ 摘　　要

NOVELTY - A neural computer (100) comprises a preprocessor (110) configured to receive an image and generate a feature map of the received image, a flattening unit (120) configured to transform the feature map generated by the preprocessor into tabular data to provide data output, and an image classifier (130) configured to classify images received through the preprocessor using the data output by the flattening unit as an input value. The preprocessor includes an optical signal processor configured to receive the image and generate the feature map. USE - Neural computer e.g. neural computer with convolution neural network or recurrent neural network is used in most computer vision applications. Uses include but are not limited to image classification, semantic segmentation, optical flow and deep learning. ADVANTAGE - The computer reduces a processing capacity of input image and time, and improves degree of integration and constructing a large area device. The computer simplifies an operation of processing an input image. DESCRIPTION OF DRAWING(S) - The drawing shows a block diagram showing a configuration of the neural computer. Neural computer (100) Preprocessor (110) Flattening unit (120) Image classifier (130)