计算机科学
班级(哲学)
模式识别(心理学)
人工智能
数字识别
培训(气象学)
语音识别
数字
机器学习
人工神经网络
数学
算术
物理
气象学
作者
Igor Ševo,Aleksandar Kelecevic
标识
DOI:10.1109/indel.2016.7797785
摘要
This paper presents a convolutional neural network clustering approach for handwritten digits recognition. Neural networks were trained individually, using the same training set and combined into clusters, depending on the training method used. These clusters formed a layered architecture, where each layer attempted to recognize the given digit, when the previous layers were not able to do so with sufficient certainty. We examine various ways of combining such clusters and training their constituent networks.
科研通智能强力驱动
Strongly Powered by AbleSci AI