I read a lot about the structure of the human brain and artificial neural networks.

Is it possible to build an AGI (or human-level AI) with artificial neural networks on neuromorphic chips, which would be divided into centers, like the brain is, e.g. centers responsible for feelings, abstract thinking, speech, memory, etc.?


No. The 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 the capacity to create abstractions on their own

  • we can't match the size/number of artificial neurons to the number of biological neurons

  • even with a much smaller ANN size, 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).

  • 4
    $\begingroup$ Both the question and answer might benefit from distinguishing between "possible someday" and "possible right now" $\endgroup$
    – antlersoft
    Oct 20 '16 at 21:17

Not the answer you're looking for? Browse other questions tagged or ask your own question.