Binary neural systems: combining weighted and weightless properties
Igor Aleksander, Tim Clarke, Antônio P. Braga · Intelligent Systems Engineering · 1994
A neural function is developed that combines the characteristics of weightless and weighted binary neurons. A new combined generalisation algorithm is presented and applied to a neural state machine which is capable of learning to respond to sequences of inputs. The difficulty with such tasks lies in learning appropriate internal state assignments. A particular ‘iconic’ method of solving this problem is discussed. The analysis includes a discussion of implementational issues.