AdaGrad Gradient Descent Method for AI Image Management
Jen-Kuang Fang, Cher‐Min Fong, Peng Yang, Chao-Kai Hung, Wenlong Lu, Chien-Wei Chang
Abstract
In this study, we used AdaGrad gradient descent method in optimizer for image deep learning, and compare with Adam gradient descent methods. After processing over six thousand huge database of through silicon via images, AdaGrad has shown a fast convergence and less generalization errors than Adam. The results help Artificial Intelligence for making the management of image judgment more accurate and faster.
Topics & Concepts
GeneralizationGradient descentComputer scienceConvergence (economics)Image (mathematics)Artificial intelligenceStochastic gradient descentDescent (aeronautics)AlgorithmMathematicsArtificial neural networkMathematical analysisEngineeringAerospace engineeringEconomic growthEconomicsAdvanced Neural Network ApplicationsRobotics and Sensor-Based LocalizationImage and Object Detection Techniques