Sir , how do we decide that how many layers we toh construct and how many perceptron each layer have ?
About layers and perceptrons
Hey @shubhambarnwal02…
There is no such rule or law to decide how many layers and perceptrons would work better.
This always depend on the data.
So. Based on practice, learning you will get an idea with what to start with.
Hence that is the only way to go forward on this.
Sir , than how we implement on a different question ? At least give some basic idea .
Deciding number of layers just comes from practice, learning about multiple models, understanding there architectures. You can try using 3 4 10 layers but decide the one to choose which has better results.
And about the perceptrons in each layers, as a gpu configuration most of the time they are choosen as of power of 2 , but there is no such rule, you can use any.
Just need to understand the approach of deciding layers and you will understand the number of perceptrons to be taken for some simple tries
1 Like
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.