Data Science Stack Exchange is a question and answer site for Data science professionals, Machine Learning specialists, and those interested in learning more about the field. It only takes a minute to sign up.
Sign up to join this community
I am starting being interested in neural networks, and I am writing some code about it. But, differently from methods like support vector machines, random forests,..etc., to me it seems more like a black box which I can't control.
So my question is:
What are methods to increase accuracy and other performances in a neural network?
Thanks in advance.
basically you should try to use regularization/dropout/batch-normalization and find out the optimal hyper-parameters to improve performance of your model.
After applying these optimizations you can use Randomized Search to find optimal hyper-parameters
