[Intro to Deep Learning with PyTorch -- L2 -- N9] Perceptron Trick

Posted answer1215

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了[Intro to Deep Learning with PyTorch -- L2 -- N9] Perceptron Trick相关的知识,希望对你有一定的参考价值。

Give this:

技术图片

 

We have a wrongn classified point, how to move the line to come closer to the points?

技术图片

We apply learning rate and since wrong point is in positive area, we need to  W - learning rate * wrong cord

 

The same, if the wrong point in negivate area, we do : W + learing rate * wrong cord:

技术图片

 

For the second example, where the line is described by 3x1+ 4x2 - 10 = 0, if the learning rate was set to 0.1, how many times would you have to apply the perceptron trick to move the line to a position where the blue point, at (1, 1), is correctly classified?

Answer: 10 times

以上是关于[Intro to Deep Learning with PyTorch -- L2 -- N9] Perceptron Trick的主要内容,如果未能解决你的问题,请参考以下文章

[Intro to Deep Learning with PyTorch -- L2 -- N15] Softmax function

[Intro to Deep Learning with PyTorch -- L2 -- N20] Cross-Entropy

[Intro to Deep Learning with PyTorch -- L2 -- N14] Sigmoid function

Intro to Machine Learning

How To Improve Deep Learning Performance

deep learning入门:感知机