I am a beginner with Neural Networksto neural networks and have had trouble grasping two concepts: (1) How does one decide the number of middle layers a given neural network has? 1 vs. 10 or whatever. (2) How does one decide the number of neurons per middle layer? Is it recommended you have an equal number of neurons in each middle layer or does it vary with the application?
- How does one decide the number of middle layers a given neural network have? 1 vs. 10 or whatever.
- How does one decide the number of neurons in each middle layer? Is it recommended having an equal number of neurons in each middle layer or does it vary with the application?