Abstract: An intangible sensor for measuring intangible properties of a substance and a method for making the sensor is described. The intangible sensor may be embodied in a mapping neural network model. The intangible sensor herein is a device that quantitatively measures complex intangible properties of a sample of a substance. The term intangible implies a subjective connotation such as in the taste, creaminess or softness of a substance or product and therefore can only be subjectively defined. Although an intangible property is known to be a function of certain measurable physical properties of a substance, there are no known definitions of this function. The intangible sensor herein can implement this function simply without having any detailed knowledge of or making any analysis of the function.

Abstract: A crossbar useful for self-routing messages is described having a return network that can return all messages, or their headers, that encounter a busy node at the output. A system is described in which this crossbar with return network can operate as a building block. It is particularly well suited to systems where truly non-blocking networks are required.

Abstract: An optical switch with a waveguide used as a detector is disclosed. The switch can be used for circuit or packet switching. The waveguide is used to tap off a fraction of the input signal going into the switch. The waveguide then sends the tapped off signal to a local electronic control to decide if switching is necessary or not. This is determined by within the local electronic control associated with the switch. The switch is set or reset based on information in the electrical representation of the signal which reaches the local electronic control. The switch can be used with continuous input signals as well as data packet input signals. By spacing the timing of data in the header differently than in the data in the "data" portion of a signal, extremely high bandwidth available in pure optical communications can be maintained.

Abstract: The disclosure relates to the use of genetic learning techniques to evolve neural network architectures for specific applications in which a general representation of neural network architecture is linked with a genetic learning strategy to create a very flexible environment for the construction of custom neural networks.