Convolutional Neural Network Training Optimization for Low Point Density Image Recognition
Vadim Ziyadinov, П. С. Курочкин, М. В. Терешонок
Abstract
Methods for structure optimization of convolutional neural network used for low point density images recognition are proposed to accelerate the training and new images recognition, as well as to reduce the training and recognition procedures resource consumption. Optimized neural network showed a significant increase in speed without accuracy drop in the low point density images recognition, as well as a significantly reduced overfitting tendency.
Topics & Concepts
OverfittingConvolutional neural networkComputer scienceArtificial intelligencePattern recognition (psychology)Training (meteorology)Artificial neural networkPoint (geometry)Image (mathematics)MathematicsPhysicsMeteorologyGeometryNeural Networks and ApplicationsAdvanced Memory and Neural ComputingOptical Polarization and Ellipsometry