Abstract: A system, method, and design structure for address-event-representation network simulation are provided. The system includes a hardware structure with a plurality of interconnected processing modules configured to simulate a plurality of interconnected nodes. To simulate each node, the hardware structure includes a source table configured to receive an input message and identify a weight associated with a source of the input message. The hardware structure also includes state management logic configured to update a node state as a function of the identified weight, and generate an output signal responsive to the updated node state. The hardware structure further includes a target table configured to generate an output message in response to the output signal, identify a target to receive the output message, and transmit the output message. The hardware structure may further include learning logic configured to combine information about input messages and generated output signals, and to update weights.

Abstract: An analog-digital crosspoint-network includes a plurality of rows and columns, a plurality of synaptic nodes, each synaptic node of the plurality of synaptic nodes disposed at an intersection of a row and column of the plurality of rows and columns, wherein each synaptic node of the plurality of synaptic nodes includes a weight associated therewith, a column controller associated with each column of the plurality of columns, wherein each column controller is disposed to enable a weight change at a synaptic node in communication with said column controller, and a row controller associated with each row of the plurality of rows, wherein each row controller is disposed to control a weight change at a synaptic node in communication with said row controller.

Abstract: An analog-digital crosspoint-network includes a plurality of rows and columns, a plurality of synaptic nodes, each synaptic node of the plurality of synaptic nodes disposed at an intersection of a row and column of the plurality of rows and columns, wherein each synaptic node of the plurality of synaptic nodes includes a weight associated therewith, a column controller associated with each column of the plurality of columns, wherein each column controller is disposed to enable a weight change at a synaptic node in communication with said column controller, and a row controller associated with each row of the plurality of rows, wherein each row controller is disposed to control a weight change at a synaptic node in communication with said row controller.

Abstract: A system, method, and design structure for address-event-representation network simulation are provided. The system includes a hardware structure with a plurality of interconnected processing modules configured to simulate a plurality of interconnected nodes. To simulate each node, the hardware structure includes a source table configured to receive an input message and identify a weight associated with a source of the input message. The hardware structure also includes state management logic configured to update a node state as a function of the identified weight, and generate an output signal responsive to the updated node state. The hardware structure further includes a target table configured to generate an output message in response to the output signal, identify a target to receive the output message, and transmit the output message. The hardware structure may further include learning logic configured to combine information about input messages and generated output signals, and to update weights.

Abstract: Neural networks for optimal estimation (including prediction) and/or control involve an execution step and a learning step, and are characterized by the learning step being performed by neural computations. The set of learning rules cause the circuit's connection strengths to learn to approximate the optimal estimation and/or control function that minimizes estimation error and/or a measure of control cost. The classical Kalman filter and the classical Kalman optimal controller are important examples of such an optimal estimation and/or control function. The circuit uses only a stream of noisy measurements to infer relevant properties of the external dynamical system, learn the optimal estimation and/or control function, and apply its learning of this optimal function to input data streams in an online manner. In this way, the circuit simultaneously learns and generates estimates and/or control output signals that are optimal, given the network's current state of learning.

Abstract: Neural networks for optimal estimation (including prediction) and/or control involve an execution step and a learning step, and are characterized by the learning step being performed by neural computations. The set of learning rules cause the circuit's connection strengths to learn to approximate the optimal estimation and/or control function that minimizes estimation error and/or a measure of control cost. The classical Kalman filter and the classical Kalman optimal controller are important examples of such an optimal estimation and/or control function. The circuit uses only a stream of noisy measurements to infer relevant properties of the external dynamical system, learn the optimal estimation and/or control function, and apply its learning of this optimal function to input data streams in an online manner. In this way, the circuit simultaneously learns and generates estimates and/or control output signals that are optimal, given the network's current state of learning.

Abstract: A method and apparatus for processing a composite acoustic signal to reconstruct an acoustic signal that substantially matches a selected one of a plurality of sources. A plurality of microphones positioned at different spatial locations detect. variations in sound pressure level resulting from the activity of a plurality of acoustic sources at different locations. The outputs of the microphones are sampled and digitized, and the resulting digital waveform from each microphone is provided as an input to a corresponding filter bank. The outputs of the filter banks are input to a comparison unit. A comparison control unit generates “signature” information that characterizes each source with respect to the microphones. The comparison unit receives “signature” information of a selected source from the comparison control unit and provides an output to a synthesizer unit which produces a synthesized digital waveform for the selected source.

Abstract: An apparatus and method produce a videotape or other recording that cannot be pre- or post-dated, nor altered, nor easily fabricated by electronically combining pre-recorded material. In order to prevent such falsification, the camera or other recording apparatus periodically receives certifiably unpredictable signals ("challenges") from a trusted source, causes these signals to influence the scene being recorded, then periodically forwards a digest of the ongoing digital recording to a trusted repository. The unpredictable challenges prevent pre-dating of the recording before the time of the challenge, while the storage of a digest prevents post-dating of the recording after the time the digest was received by the repository.

Abstract: A method and apparatus authenticates and provides non-reputability for analog messages which renders it impossible for a person, including the recipient, who is not in possession of a (cryptographic) key belonging to the claimed sender, to forge the message. The recipient is able to verify that the sender possessed the correct key, and a third party (judge) can establish whether the message was forged or not. This is accomplished by interposing a digital signature generator/verifier/recorder (DS-GVR) module in the sending apparatus, such as a facsimile machine. The receiver, using another DS-GVR, can verify that a received document comes from the purported sender and has not been altered enroute. The receiver's DS-GVR module can be made to produce a machine-readable record of the signed transmission.

Abstract: A method and apparatus authenticates and provides non-repudiability for analog messages which renders it impossible for a person, including the recipient, who is not in possession of a (cryptographic) key belonging to the claimed sender, to forge the message. The recipient is able to verify that the sender possessed the correct key, and a third party (judge) can establish whether the message was forged or not. This is accomplished by interposing a digital signature generator/verifier/recorder (DS-GVR) module in the sending apparatus, such as a facsimile machine. The receiver, using another DS-GVR, can verify that a received document comes from the purported sender and has not been altered enroute. The receiver's DS-GVR module can be made to produce a machine-readable record of the signed transmission.

Abstract: An inadvertent-off-hook-condition detecting apparatus for use with a telephone connected to a telephone system is described. The telephone has a hookswitch which connects the voice network of the telephone system across the input lines to the telephone when the hookswitch is in an off-hook position, and which disconnects the voice network from the telephone input lines when the hookswitch is in an on-hook position.

Abstract: A connection arrangement includes a plurality of sets of wiring planes, wherein any connection uses one and only one set of the planes. Each plane is a principal wiring direction. Various economies are affected by arranging the relationship between pairs of wiring planes in a set to have principal wiring directions lying at an acute angle. In one preferred embodiment each set includes a pair of planes and the acute angle between principal wiring directions is 45.degree..

Abstract: A method for distributing wire load among the layers of a multilayer interconnection package such that in each region of the package, the wire load is balanced among all layers and such that specified subsets of two-pin connections may be constrained to lie within the same layer.

Abstract: In printed circuit boards having dense printed connections, cross talk noise immunity is significantly improved by preferentially routing adjacent to one another serially connected conductors of the same net rather than conductors of different nets. By such routing inter-net cross talk is reduced while the resultant intra-net cross talk is maintained at tolerable levels.

Abstract: A method for establishing connections by automatically routing a plurality of paths between individual components using initially simple connection path shapes. The method is used to create an interconnection package with better use of wiring space. Each connection, in turn, is removed if previously routed, rerouted and evaluated according to specified penalty costs to minimize undesirable routing characteristics. This method is particularly advantageous in providing automatic path routing in directionally uncommitted planes for wiring highly integrated electric circuits, or the like.

Abstract: A method for establishing interconnections in the vicinity of congested clusters of pins in a printed circuit using an extended escape region in combination with an escape region and a global region. The extended escape region includes wire path segments in one signal plane of a plane pair which may enter the extended escape region from the escape region in a direction angularly disposed to the predominant direction of wiring in that plane. All wire segments exit the extended escape region to said global region in the predominant direction for the signal plane on which the interconnection is disposed.