First time here? Checkout the FAQ!
x
+3 votes
557 views
asked in Machine Learning by (660 points)  
I am wondering why should we use machine learning instead of deep learning. We know that deep learning is very powerful. Anything which machine learning algorithm can do deep learning could achieve that.

Plus using deep learning we don't have to worry about feature extraction, data cleaning etc.

So why should we use machine learning algorithms instead of deep learning ?
  

1 Answer

+1 vote
answered by (116k points)  
The first big reason is the fact training deep neural networks requires big data which is not always available. I will update this post in future with more details.
commented by (660 points)  
+1
It seems like that's not always the case. If we look at the Default of credit card clients data-set the best predictor is the neural nets and that data-set is not even big only 30000 samples. Same with the minst dataset the best predictor is convolution nets.

I am not sure if its fair to say that for deep neural networks we require tons of data. Thoughts ?
commented by (116k points)  
You are right somehow, however neural nets are different from deep neural nets which is called deep learning. For MNIST, dataset, we already, somehow, have big data, and the number of classes are small (10 classes). Take a look at this short article:

https://towardsdatascience.com/three-reasons-that-you-should-not-use-deep-learning-15bec517b622
...