英语翻译
英语翻译
Learning in such a network proceeds the same way as for perceptrons:example inputs are presented to the network,and if the network computes an output vector that matches the target,nothing is done.If there is an error (a difference between the output and target),then the weights are adjustec to reduce this error.The trick is to assess the blame for an error and divide it among the contributing weights.In perceptrons,this is easy because there is only one weight between each input and the output.But in multilayer networks.There are many weights connecting each input to an output,and each of these weights contributes to more than one output.
在这样一个网络学习收益,感知器相同的方式:例如输入提交给网络,如果网络计算的输出向量相匹配的目标,不采取任何行动.如果有一个错误(一产出和目标之间的差异),则权重adjustec减少这种误差.诀窍是评估错误引咎鸿沟在造成重了.在感知,这很容易,因为只有一间每个输入和输出的重量.但在多层网络.有连接每个输入到输出许多重量,而这些重量每有助于多个输出.
The back-propagation algorithm is a sensibly approach to dividing the contribution of each weight.As in the perceptron learning algorithm,we try to minimize the error between each target output and the output actually computed by the network.At the output layer,the weight update rule is very similar to the rule for the perceptron.There are two differences:the activation of the hidden unit aj is used instead of the input value; and the rule contains a term for the gradient of the activation function.If Erri is the error (Ti-Oi) at the output node,then the weight update rule for the link from unit j to unit i is
反向传播算法是一种明智的方法来划分,每个重量的贡献.正如在感知学习算法,我们尽量减少各目标之间的输出和实际的网络计算的输出错误.在输出层,重量更新规则非常类似的感知规则.有两点不同:隐藏的单元欧塞尔激活,而不是输入值使用;和规则包含了激活功能梯度的一个术语.如果Erri是在输出节点错误(钛爱),那么从单位重量的链接j到我单位更新规则
Wj,i
Learning in such a network proceeds the same way as for perceptrons:example inputs are presented to the network,and if the network computes an output vector that matches the target,nothing is done.If there is an error (a difference between the output and target),then the weights are adjustec to reduce this error.The trick is to assess the blame for an error and divide it among the contributing weights.In perceptrons,this is easy because there is only one weight between each input and the output.But in multilayer networks.There are many weights connecting each input to an output,and each of these weights contributes to more than one output.
在这样一个网络学习收益,感知器相同的方式:例如输入提交给网络,如果网络计算的输出向量相匹配的目标,不采取任何行动.如果有一个错误(一产出和目标之间的差异),则权重adjustec减少这种误差.诀窍是评估错误引咎鸿沟在造成重了.在感知,这很容易,因为只有一间每个输入和输出的重量.但在多层网络.有连接每个输入到输出许多重量,而这些重量每有助于多个输出.
The back-propagation algorithm is a sensibly approach to dividing the contribution of each weight.As in the perceptron learning algorithm,we try to minimize the error between each target output and the output actually computed by the network.At the output layer,the weight update rule is very similar to the rule for the perceptron.There are two differences:the activation of the hidden unit aj is used instead of the input value; and the rule contains a term for the gradient of the activation function.If Erri is the error (Ti-Oi) at the output node,then the weight update rule for the link from unit j to unit i is
反向传播算法是一种明智的方法来划分,每个重量的贡献.正如在感知学习算法,我们尽量减少各目标之间的输出和实际的网络计算的输出错误.在输出层,重量更新规则非常类似的感知规则.有两点不同:隐藏的单元欧塞尔激活,而不是输入值使用;和规则包含了激活功能梯度的一个术语.如果Erri是在输出节点错误(钛爱),那么从单位重量的链接j到我单位更新规则
Wj,i
英语人气:970 ℃时间:2019-12-12 00:38:53
优质解答
看到BP了,如果不出所料应该是神经网络的内容不要相信翻译软件,帮你重翻了一遍:术语:weight 权重hidden unit 隐层Learning in such a network proceeds the same way as for perceptrons: example inputs are prese...
我来回答
类似推荐
猜你喜欢
- 1《生命的价值》阅读答案
- 2My life will be a lot better对a lot better提问.()()()()your life will be like?
- 3写一篇以 发生在班级里的一件事 的500字作文
- 4Nice to meet you.话题小短文
- 5《童年的发现》"我"发现了什么?是怎样发现的?
- 6设a,b为实数,i为虚数单位,且(a+bi)(3+i)=10+10i,则ab的值为( ) A.2 B.4 C.8 D.16
- 7气球以10m/s的速度匀速上升,在离地面75m高处从气球上掉落一个物体,不计物体在运动过程中受到的空气阻力,问:
- 8(2/2)前氮气和氢气的体积比为多少 氮气的平衡转化率为多少 平衡混合气体中氨气的体积分数
- 9若a的模等于1,b的模等于根号2,且(a向量—b向量)垂直于a向量,则a向量与b向量的夹角为
- 10如图,求出这个图形的周长和面积