# How to train the deep neural network efficiently when the input data are unstructured

Background

So the background is that I want to use a deep neural network to model a system. In a traditional way to observe the system character, we will use the Gaussian noise as the inputs of the system, and then we could obtain the outputs of the system. Now I want to use the Gaussian noise (inputs) and the obtained outputs to train a deep neural network, an end-to-end model, to model this system.

Question

If the data are structured, we can pre-train the networks layer by layer with auto-encoder to obtain a well-enough initial value of the weights. However, the inputs now are totally unstructured (Gaussian noise). How should I efficiently train the deep neural network I want? Are there some prior works on this issue?

• you don't need to pretrain weights – shimao Apr 24 at 19:57
• @shimao You mean I just need to try other ways like using ReLu, ResNet structure? – Yuejiang_Li Apr 25 at 0:54
• i mean that it is usually unnecessary to pretrain network weights in most cases – shimao Apr 25 at 1:57
• Yes, I asked many people and they gave me the same answer. This problem is actually from my artificial neutral network homework. I think this problem is kinda weird, though. Thanks for your answer, anyway. – Yuejiang_Li Apr 25 at 3:18