No, deep learning algorithms automatically learn features from the data. This makes them sometimes difficult to interpret and less generalizable, but also very powerful for complicated classification problems.

Thank you sir

The main difference between machine learning and deep learning is about features selection. deep learning does not need to specify features and it could extract them automatically from training data.

DEAR Gunikhan Sonowal

Feature selection is the process of reducing the number of input variables when developing a predictive model. It is desirable to reduce the number of input variables to both reduce the computational cost of modeling and, in some cases, to improve the performance of the model. So, the conclusion is that Deep Learning Networks do not need a previous feature selection step. I agree with the other mentioned answers.

GOOD LUCK

Dear Gunikhan Sonowal :

The simple Answer is a BIG NO. Deep learning algorithms only extract features, and features go from local to an abstract level. Feature selection in Deep learning is still an unexplored area due to the black-box nature of DL.

Regards;

Ehtisham