Our current ML Neural Networks work (simplified) like this: A neuron emits a number and the next neuron calculates a new number to emit based on all the values given to it by other neurons as inputs. Our brain can't fire numbers in this way. So there's a fundamental difference. Bridging this difference to create NNs that are more similar to our brains is the basis of the study of Spiking Neural Networks. Their performance so far isn't great, but it's an interesting topic of research.