Are there any architectures of deep neural networks that connect input neurons not only with the first hidden layer but also with deeper ones (red lines on the picture)?
If so could you give some names or links to research papers?
Artificial Intelligence Stack Exchange is a question and answer site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment. It only takes a minute to sign up.
Sign up to join this communityAre there any architectures of deep neural networks that connect input neurons not only with the first hidden layer but also with deeper ones (red lines on the picture)?
If so could you give some names or links to research papers?
This type of connections are called skip or residual connections. There are numerous works which employs this type of mechanism, for example: ResNet, SkipRNN. In addition here you can find a paper that empirically explores the skip connections for sequential tagging, or this one for speech enhancement.