加拿大的startup 的一道数据题

以下一道题是我在面试中发的题，感觉是错的，不应该是x_i 而应该是y_i.我重新注册了帐号发的题，因为以前的帐号暴漏名字，求加分啊

Assume that for a standard feed-forward neural network, the objective function is defined as:

F(w) = Sum_i V(x_i, z_i);

where 'i' is the time index of the incoming feature vectors, x_i is an i\th feature vector, z_i is the output of the neural, V(x_i, z_i) represents some error function between x_i and z_i, Sum_i represent a summation func

您好！
本帖隐藏的内容需要积分高于 188 才可浏览
您当前积分为 0。
使用VIP即刻解锁阅读权限或查看其他获取积分的方式

游客，您好！
本帖隐藏的内容需要积分高于 188 才可浏览
您当前积分为 0。
VIP即刻解锁阅读权限 或 查看其他获取积分的方式
Unlock interview details and practice with AI
Curated Interview Questions from Top Companies

suming that V is the cross entropy objective criterion.

3b) What is the impact of this modification on the computational complexity of training as well as inference of the neural network. Suggest an effective way of implementing this neural network in code.