Some Properties of Small Networks of Randomly Connected Artificial Neurons

Much of the work on b r a i n models in the l a t e 1950's and ea r l y 1960's comprised the cons t ruc ­ t i o n , e i t h e r in hardware, or more commonly by s imu la t i on on a d i g i t a l computer, of networks of a r t i f i c i a l neurons (he rea f te r the term 'neuron' w i l l r e f e r t o a r t i f i c i a l neurons, where necessary b r a i n c e l l s w i l l be r e f e r r e d as ' n a t u r a l neu rons ' ) . H i s t o r i c a l l y the idea networks o f neurons per forming b r a i n l i k e func t ions stems from the work of McCulloch and P i t t s .