Convolutional neural model in a TASK of classification images of the isolated digits

Abstract

The analysis of convolutional neural model is done. The software is developed, allowing to train and test convolutional neural networks of base architecture LeNet-5. Efficiency of technique multi training and distortions of training images is shown. The qualifier of images of the isolated figures is constructed. The estimation of stability of its characteristics on examples of known hand-written and font databases is done.

Keywords

• mnist