admin管理员组

文章数量:1122832

I am learning about neural networks, so I started experimenting with Tensorflow playground.

to understand the basics I set all parameters manually and didn't train the model afterward. specifically I set the weights to 1 and -1, and the baises to zero. However, the output result surprised me, and I have alot of questions:

  1. why is there a blue area in the output? Shouldn't that area have a vlue of zero and therefore be white?
  2. If presence of blue area makes sense, why is it shifted upward and to the right?
  3. why does the middle of the plot have a trimmed corner instead of a 90-degree corner?

本文标签： deep learningUnderstanding the output of a simple neural network in TensorFlow PlaygroundStack Overflow

版权声明：本文标题：deep learning - Understanding the output of a simple neural network in TensorFlow Playground - Stack Overflow 内容由网友自发贡献，该文观点仅代表作者本人， 转载请联系作者并注明出处：http://www.betaflare.com/web/1736307173a1933219.html， 本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌抄袭侵权/违法违规的内容，一经查实，本站将立刻删除。