How is reward-punishment used to separate 2-D patterns such that (0,0)T and (0,1)T represent one class (ω1 ) and (1,0)T and (1, 1)T to represent a second class (ω2 )? If it can separate these pattern...

How is reward-punishment used to separate 2-D patterns such that (0,0)T and (0,1)T represent one class (ω1 ) and (1,0)T and (1, 1)T to represent a second class (ω2 )? If it can separate these pattern classes, explain how to check that the reward-punishment procedure converges.