how to decide what activation function to choose and how many layers?
using relu and 3 layers my loss reached 2795820.2218 as minimum why is this so?
Features selection
hey @ayangiri3 ,
choosing activation function and number of layers is task under hyper parameter tuning for deep learning.
There is no such particular criteria or method to choose it as such , you just can try different combinations and find the one which works the best for your dataset.
After performing a large number of such combinations you will get in some practice about these and can make better models more fastly.
for this can you please share your code with me , so that i can understand your approach.
Thank you.
I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.
On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.