- 今天再看一位大哥的blog的时候，突然发现，他说的很有道理，机器学习这个东西本来就是很实践性的东西, 要做什么, 拿个例子先跑通了，然后兴趣进去了。带着兴趣再去研究理论，这个才是我研究机器学习应该遵循的方式。
理论知识小结： - 1 神经网络更新参数的方式，通俗的解释 w' = w - a(J/w(i))：
参考：http://blog.csdn.net/u013230651/article/details/75909596 - 参考：https://www.leiphone.com/news/201705/TMsNCqjpOIfN3Bjr.html
实践项目：
项目1 ：神经网络实现手写数字识别
参考网址：
- 关于手写识别中的输入和输出神经元的个数其实都是经验的，因为我们并不知道实际神经网络的学习规则
- [2]中对于目标函数为何选择二次损失函数，而不是选择最大正确分类个数的解释：因为二次函数是模型中权重参数和阈值参数的连续函数，因此对于权重和阈值的微小变化都可以反映出来，利于调整参数，而最大分类正确个数就不具有找个性质
Why introduce the quadratic cost? After all, aren't we primarily interested in the number of images correctly classified by the network? Why not try to maximize that number directly, rather than minimizing a proxy measure like the quadratic cost? The problem with that is that the number of images correctly classified is not a smooth function of the weights and biases in the network. For the most part, making small changes to the weights and biases won't cause any change at all in the number of training images classified correctly. That makes it difficult to figure out how to change the weights and biases to get improved performance. If we instead use a smooth cost function like the quadratic cost it turns out to be easy to figure out how to make small changes in the weights and biases so as to get an improvement in the cost. That's why we focus first on minimizing the quadratic cost, and only after that will we examine the classification accuracy.
