OINNIONN: outward inward neural network and inward outward neural network evolution

Neural networks perform well when they are built for a specific task and the set of inputs and the set of outputs are well defined. However, these results are very limited in scope, and communication between different neural networks to share knowledge that can lead to the performance of more general tasks is still inadequate. Communication between specialized neural networks is the goal of the present work. We utilize independent sets of neural networks trained for specific tasks, while transferring knowledge among the neural networks allows them to evolve chaining the input and output information. The idea is based on computer network architecture, which is a communication system that transfers data between components inside a computer or between computers. The idea can similarly allow each neural network to specialize in its own task while transferring and receiving information from other neural networks. This can allow different neural networks to be plugged in and knowledge transfer to evolve. It can also allow additional information to be requested, when the task at hand is difficult or hard to resolve.