Neurons and Synapres

I get asked is why the neural morphic computer needs to be a computer chip. It works on the neurobiological architecture of the brain. Traditional computers cannot map this because it uses classical von Neumann principles of a processor, storage, and network. That is up to now how we built neural networks.  Morphic computing is different from the traditional path neural networks. Neural morphic computing changes the theorem, so the structure is the processor is in the middle of everything.
The chips inspired by neurons in the way that they process information and sensory and visual thinking  and this utilizing very little energy.  The new chips look like neurons in the brain. They seem entirely biological, listening to all modal inputs and including vision with these morphic chips. We needed to build different architectures from a different  technology.  It uses an electronic rods to connect the neurons. That relates them to the way we think of the brain functioning using nanotechnologies; it looks like a brain. These connectors are tiny and thin synapses between the network so that short-term memory is combined with processing making the short-term memory versus long-term memory derived from the short-term memory. It needs no neurons. We then reinforced repetition the patterns  of how our neurons work are revealed.  Based on research into how our brain works.
The connections between neurons get stronger as the repetition builds our ability to be skilled, and knowledgeable is to have the strong connection between the sections of neurons. We learn to develop these connections in relationships to skills and knowledge. We started making structures that we are self-visualizing the neurons the synapse and connects how they relate the human brain. This why the context of health, self-driving and machine learning are complementary. The chip interprets itself. Then Machine Learning can be evaluating the results of the morphic computer that help each other that determine the level of acceptable ranges of their what limitations regarding what you always want a resultant synaptic value to the stimuli.