I read a lot about the structure of the human brain and artificial neural networks. I wonder if it is possible to build an artificial intelligence with neural networks that would be divided into centers such as the brain is, e.g. centers responsible for feelings, abstract thinking, speech, memory, etc.?
No. Reasons include, but are not limited to:
- lack of understanding of how the brain works
- current ANNs are mostly good at pattern recognition and generative tasks, but lack capacity to create abstractions on their own
- we cant match size/number of perceptrons to number of neurons
- even with much smaller ANN size network, performance is an issue (i.e. state of the art image categorization ANNs have to be trained few weeks on multi GPU rigs to match human level).