Ch 2. Learning Processes Learning Learning is a process by which free parameters of NN are adapted thru stimulation from environment Sequence of Events stimulated by an environment undergoes changes in its free parameters responds in a new way to the environment Learning Algorith m prescribed steps of process to make a system learn ways to adjust synaptic weight of a neuron No unique learning algorit hms - kit of too ls The Chapter cover s five learning rules, learning paradigms, issues of learning task probabilistic and statistical aspect of learning Error Correction Learning(I) Error signal, ek(n)ek(n) = d k(n ) - y k(n)where ndenotes time step Error signal activates a control mechanism for corrective adjustment of synaptic weights Mininizing a cost function, E(n) , or index of performance Also called instantaneous value of error energy step-by-step adjustment until system reaches steady state; synaptic weights are stabilized ) ( 2 1 ) ( 2 nnEekError Correction Learning(II) Deltra rule, Widrow-Hoff rule wkj(n)= ek(n)xj(n). What is more general rule of delta rule? : rate of learning ; learni ng-rate parameter wkj( n+ 1 ) = wkj( n) + wkj( n) wkj( n) = Z -1 [ wkj( n+ 1 ) ] Z -1 is unit-delay operator adjustment is propo rtioned to the pro duct of error signal and input signal error-correction learning is local The learning rate determines the stability or convergence