阅读说明：本技术 神经网络训练系统、方法和计算机可读存储介质 (Neural metwork training system, method and computer readable storage medium ) 是由 费旭东 于 2018-03-19 设计创作，主要内容包括：一种神经网络训练系统、方法和计算机可读存储介质,属于机器学习算法领域。所述神经网络训练系统(300)包括：第一处理设备(301)和第二处理设备(302),其中,第一处理设备(301)用于获取目标神经网络的权向量和训练集中的N个数据向量,并基于N个数据向量中的每一个数据向量和权向量进行第一运算得到N组输出值,第一运算包括向量点积运算；第二处理设备(302),用于获取根据N组输出值计算得到的至少一个修正值,并根据至少一个修正值对第二处理设备(302)中存储的神经网络的权向量中的向量元素进行修正,得到修正权向量,并将修正权向量发送至第一处理设备(301)。提供的神经网络训练系统能够提高神经网络训练的效率。(A kind of neural metwork training system, method and computer readable storage medium, belong to machine learning algorithm field.The neural metwork training system (300) includes: the first processing equipment (301) and second processing equipment (302), wherein, first processing equipment (301) is used to obtain N number of data vector in the weight vector and training set of target nerve network, and the first operation is carried out based on each of N number of data vector data vector and weight vector and obtains N group output valve, the first operation includes dot product operation；Second processing equipment (302), for obtaining at least one correction value being calculated according to N group output valve, and the vector element in the weight vector of the neural network stored in second processing equipment (302) is modified according at least one correction value, amendment weight vector is obtained, and amendment weight vector is sent to the first processing equipment (301).The neural metwork training system of offer can be improved the efficiency of neural metwork training.)