Learning Processes.pptVIP

jkim@cs.kaist.ac.kr Learning Processes CS679 Lecture Note by Jin Hyung Kim Computer Science Department KAIST 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 Algorithm prescribed steps of process to make a system learn ways to adjust synaptic weight of a neuron No unique learning algorithms - kit of tools The Chapter covers 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) = dk(n) - yk(n) where n denotes 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 Also called deltra rule, Widrow-Hoff rule Error Correction Learning(II) ?wkj(n) = ?ek(n)xj(n) ? : rate of learning; learning-rate parameter wkj(n+1) = wkj(n) + ?wkj(n) wkj(n) = Z-1[wkj(n+1) ] Z-1 is unit-delay operator adjustment is proportioned to the product of error signal and input signal error-correction learning is local The learning rate ? determines the stability or convergence Memory-based Learning Past experiences are stored in memory of correctly classified input-output examples retrieve and analyze “local neighborhood” Essential Ingredient Criterion used for defining local neighbor Learning rule applied to the training examples Nearest Neighbor Rule (NNR) the vector X’n ? { X1, X2, …,XN } is the nearest neighbor of Xtest if X’n is the class of Xtest Nearest Neighbor Rule Cover and Hart Examples are independent and identically distributed The sample size N is infinitely large then, error(NNR) 2 * error(Bayesian rule) Half of