| Ellman, J. (1990). Finding structure in time. Cognitive Science 14, 179-211. |
....are fairly immune to static or background noise. The underlying architecture of the neuron model is the Jordan Elman neural network shown in Figure 3. The Jordan Elman model is an example of a simple recurrent neural network that was introduced by Jordan [38] and subsequently modi ed by Elman [10] to include a short term memory (STM) using context units. The context units in the input layer hold a copy of the activation of the hidden layer from the previous time step. Fully connected recurrent neural networks have been shown to be capable of implementing any arbitrary nite state automata ....
Ellman, J. (1990). Finding structure in time. Cognitive Science 14, 179-211.
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