机器学习进入模型的数据
With the rapid expansion of Machine Learning as a field of research, it’s not easy to keep up with everything that is being invented and discovered.
随着机器学习作为研究领域的Swift发展,跟上发明和发现的一切变得不容易。
I have created a graph that will make the distinction of the types of machine learning systems easier to understand.
我创建了一个图表,使机器学习系统类型的区别更容易理解。
It is useful to keep in mind there’s more than one way (ML algorithm) to solve a specific problem. Usually, there are several that fit and it’s your duty to identify which is the best algorithm with the given circumstances of its implementation.
请记住,解决特定问题的方法不止一种(ML算法),这很有用。 通常,有几种合适的算法,在给定的实现条件下,确定哪种算法是最佳算法是您的责任。
Nowadays, everything is being solved with neural networks; why use a sword to cut bread, when a knife would be sufficient?
如今,一切都可以通过神经网络解决。 为什么用刀切面包,用刀就足够了?
The ML landscape looked from above, has mainly four different directions:
从上面看,机器学习的情况主要有四个不同的方向:
![Image for post](https://i-blog.csdnimg.cn/blog_migrate/c211e4e955c441b83901d4103408c859.png)
In the following weeks, I will delve into each topic and discuss its nuts and bolts.
在接下来的几周中,我将深入研究每个主题并讨论其基本内容。
总结 (Sum up)
Hope this article helped you get a clearer idea how the ML landscape is generally separated.
希望本文能帮助您更清楚地了解ML领域通常是如何分离的。
Did I miss any types of learning? Let me know in the comments below.
我错过任何学习方式吗? 在下面的评论中让我知道。
I’d love to hear your ideas on what you’d like to read next — let me know down below in the comment section!
我很想听听您对接下来要读的内容的想法-请在下面的评论部分中告诉我!
You can always connect with me via LinkedIn.
您可以随时通过LinkedIn与我联系。
翻译自: https://medium.com/@bardhrushiti/navigating-into-the-world-of-machine-learning-1c1b10ae40b
机器学习进入模型的数据