Ten Recommendations for Training Neural Networks
IN THIS CHAPTER
Preprocessing data to ensure suitable analysis
Selecting the weights and layers of a neural network
Choosing an activation function to produce acceptable output
In most software development efforts, an application will always do its job if you code it correctly. But when you work with neural networks, this isn’t the case. You can write flawless code and still end up with lousy results. No matter what the academics say, neural network development is not an exact science — there’s still a lot of art involved.
In this chapter, I present ten recommendations that can help you improve the accuracy and performance of your neural networks. These general rules are based on my experience and what I’ve learned from other developers and researchers. But keep in mind that neural networks are never completely reliable: Even a perfectly coded neural network can fail from time to time.
Select a Representative Dataset
This recommendation is the simplest because it doesn’t involve any math or software development. When it comes to training samples, more is better, but size isn’t the only priority. You need to make sure ...