Where is the brain inside the brain?On why artificial neural networks should be developmental

Biological brains are capable of general learning without supervision. This is learning across multiple domains without interference. Unlike artificial neural networks, in real brains, learned information is not purely encoded in real-valued weights but instead it resides in many neural aspects. Such aspects include, dendritic and axonal morphology, number and location of synapses, synaptic strengths and the internal state of neural components. Natural evolution has come up with extraordinary ‘programs’ for neurons that allow them to build learning systems through group activity. The neuron is the ‘brain within the brain’. We argue that evolving neural developmental programs which when executed continuously build, shape and adjust neural networks is a promising direction for future research. We discuss aspects of neuroscience that are important, and examine a model that incorporates many of these features that has been applied to a number of problems: wumpus world, checkers and maze solving.