24小时热门版块排行榜

返回列表

当前只显示满足指定条件的回帖，点击这里查看本话题的所有回帖

xuh1991

木虫 (正式写手)

应助: 0 (幼儿园)
金币: 2764.5
帖子: 508
在线: 77.2小时
虫号: 3945940
注册: 2015-06-29
性别: GG
专业: 信号理论与信号处理

[求助] BP神经网络和梯度下降法的疑问？已有2人参与

在BP神经网络中，默认的训练函数就是梯度下降法，即按照梯度下降法来更新权值，那么这样的BP神经网络和梯度下降法的区别在哪里呢？

回复此楼

» 猜你喜欢

国基评审已经有10人回复
析晶已经有5人回复
国自然面上和省基金B类撒花已经有22人回复
2026-博士申请已经有4人回复
26级硕士毕业生求博导收留已经有4人回复
湖南大学刘巧玲课题组2026年第二批次博士研究生招生信息已经有6人回复
考研调剂已经有3人回复
急招9月入学博士，要有4级、最晚7月硕士毕业。精密电机驱控课题；学位材料已经有5人回复
又一批高校组建人工智能学院师资行吗不是骗人吗已经有7人回复
有没有学校收留已经有3人回复

1楼 2016-09-02 08:56:53

已阅回复此楼关注TA 给TA发消息送TA红花 TA的回帖

FMStation

至尊木虫 (知名作家)

应助: 591 (博士)
贵宾: 0.03
金币: 18688.7
红花: 97
帖子: 8891
在线: 1491.8小时
虫号: 2400059
注册: 2013-04-04
专业: 计算机应用技术

【答案】应助回帖

感谢参与，应助指数 +1

An analogy for understanding gradient descent

The basic intuition behind gradient descent can be illustrated by a hypothetical scenario. A person is stuck in the mountains and is trying to get down (i.e. trying to find the minima). There is heavy fog such that visibility is extremely low. Therefore, the path down the mountain is not visible, so he must use local information to find the minima. He can use the method of gradient descent, which involves looking at the steepness of the hill at his current position, then proceeding in the direction with the steepest descent (i.e. downhill). If he was trying to find the top of the mountain (i.e. the maxima), then he would proceed in the direction steepest ascent (i.e. uphill). Using this method, he would eventually find his way down the mountain. However, assume also that the steepness of the hill is not immediately obvious with simple observation, but rather it requires a sophisticated instrument to measure, which the person happens to have at the moment. It takes quite some time to measure the steepness of the hill with the instrument, thus he should minimize his use of the instrument if he wanted to get down the mountain before sunset. The difficulty then is choosing the frequency at which he should measure the steepness of the hill so not to go off track.

https://en.wikipedia.org/wiki/Fi ... o_input_weights.png

In this analogy,
the person represents the backpropagation algorithm, and
the path taken down the mountain represents the sequence of parameter settings that the algorithm will explore.
The steepness of the hill represents the slope of the error surface at that point.
The instrument used to measure steepness is differentiation (the slope of the error surface can be calculated by taking the derivative of the squared error function at that point).
The direction he chooses to travel in aligns with the gradient of the error surface at that point.
The amount of time he travels before taking another measurement is the learning rate of the algorithm.

https://en.wikipedia.org/wiki/Ba ... ng_gradient_descent