Assume that I want to solve an issue with a neural network that either I can't fit to already existing topologies (perceptron, Konohen, etc) or I'm simply not aware of the existence of those or I'm unable to understand their mechanics and I rely on my own instead.

How can I automate the choice of the topology (that is, the number of layers, the type of activations, the type and direction of the connections, etc.) of a neural network for an arbitrary problem?

I'm a beginner, yet I realized that in some topologies (or, at least in perceptrons) it is very hard if not impossible to understand the inner mechanics as the neurons of the hidden layers don't express any mathematically meaningful context.

Assume that I want to solve an issue with a neural network that either I can't fit to existing architectures (perceptron, Konohen, etc) or I'm simply not aware of the existence of those or I'm unable to understand their mechanics and I rely on my own instead.

How can I automate the choice of the architecture/topology (that is, the number of layers, the type of activations, the type and direction of the connections, etc.) of a neural network for an arbitrary problem?

I'm a beginner, yet I realized that in some architectures (or, at least, in perceptrons) it is very hard if not impossible to understand the inner mechanics, as the neurons of the hidden layers don't express any mathematically meaningful context.

Assume that I want to solve an issue with neural network that either I can't fit to already existing topologies (perceptron, Konohen, etc) or I'm simply not aware of the existence of those or I'm unable to understand their mechanics and I rely on my own instead.

How can I deconstruct a problem to find a corresponding neural network topology? By this I don't mean only the size of certain layers, but the number of them, the type of activation functions, the number and the direction of connections, and so on.

I'm a beginner, yet I realized that in some topologies (or, at least in perceptrons) it is very hard if not impossible to understand the inner mechanics as the neurons of the hidden layers don't express any mathematically meaningful context.

Assume that I want to solve an issue with a neural network that either I can't fit to already existing topologies (perceptron, Konohen, etc) or I'm simply not aware of the existence of those or I'm unable to understand their mechanics and I rely on my own instead.

How can I automate the choice of the topology (that is, the number of layers, the type of activations, the type and direction of the connections, etc.) of a neural network for an arbitrary problem?

I'm a beginner, yet I realized that in some topologies (or, at least in perceptrons) it is very hard if not impossible to understand the inner mechanics as the neurons of the hidden layers don't express any mathematically meaningful context.