E. Oja, A simpli"ed neuron model as a principal component analyser, J. Math. Biol. 15 (1982) 267}273.  Home/Search   Document Not in Database   Summary   Related Articles

.... the hidden neurone output is real valued, quantization is required for xed length entropy coding which is normally designed as 32 level uniform quantization corresponding to 5 bit entropy coding [9,14] This neural network development, in fact, is in the direction of K L transform technology [17,21,50] which actually provides the optimum solution for all linear narrow channel type of image compression neural networks [17] When Eqs. 2.1) and (2.2) are represented in matrix form, we have [h] #[x] 2.4) xN ] #] h] #] #[x] 2.5) for encoding and decoding. The K L transform maps input ....

....(t) the ith output value; X(t) the input vector, corresponding to each individual image block and # ) # the Euclidean norm used to normalize the updated weights and make the learning stable. From the above basic Hebbian learning, a socalled linearized Hebbian learning rule is developed by Oja [50,51] by expanding Eq. 2.16) into a series from which the updating of all coupling weights is constructed from below: t)##[h (t)X(t) h# (t) t) 2.17) To obtain the leading M principal components, Sanger [58] extends the above model to a learning rule which removes the previous ....

E. Oja, A simpli"ed neuron model as a principal component analyser, J. Math. Biol. 15 (1982) 267}273.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC