embedded-analog-intelligence

robotics is more than AI, robotics needs AI embedded in the system (fed from real time sensors data and planning and adjusting in real-time its actions).

Spike time dependant

16 Nov 2018 » theory

are ANN any close to neurones? most likely not since we are still ensure about how “biological neurones” operate.

Most likely our ANN are closer to another form of network computing, see this other EAI post about tiers of cognition

eLife publication

Neurons encode information in the form of electrical signals called spikes. 
Certain neurons increase the rate at which they produce spikes under specific circumstances, e.g., whenever an animal hears a particular sound. 
These neurons are said to be 'classically responsive'. But not all neurons behave in this way. 
*Others produce spikes at a variable rate that does not obviously relate to the animal's behavior. 
These neurons are said to be 'non-classically responsive'. *
They are often omitted from analyses, despite typically outnumbering their classically responsive counterparts. 
So, what are these neurons doing?

(emphasis mine)

Question:

  • how much can we improve on our ANN designs? Most likely a lot but noone knows where (yet) :)