Abstract: Techniques are given for determining the data transmission or sending rates in a router or switch of two or more input queues in one or more input ports sharing an output port, which may optionally include an output queue. The output port receives desired or requested data from each input queue sharing the output port. The output port analyzes this data and sends feedback to each input port so that, if needed, the input port can adjust its transmission or sending rate.

Abstract: Techniques are given for determining the data transmission or sending rates in a router or switch of two or more input queues in one or more input ports sharing an output port, which may optionally include an output queue. The output port receives desired or requested data from each input queue sharing the output port. The output port analyzes this data and sends feedback to each input port so that, if needed, the input port can adjust its transmission or sending rate.

Abstract: Techniques are given for determining the data transmission or sending rates in a router or switch of two or more input queues in one or more input ports sharing an output port, which may optionally include an output queue. The output port receives desired or requested data from each input queue sharing the output port. The output port analyzes this data and sends feedback to each input port so that, if needed, the input port can adjust its transmission or sending rate.

Abstract: Techniques are given for determining the data transmission or sending rates in a router or switch of two or more input queues in one or more input ports sharing an output port, which may optionally include an output queue. The output port receives desired or requested data from each input queue sharing the output port. The output port analyzes this data and sends feedback to each input port so that, if needed, the input port can adjust its transmission or sending rate.

Abstract: A device for re-randomizing probabilistic pulse trains. The device receives an input probabilistic pulse train and produces an output probabilistic pulse train of equal value, but which is statistically independent from the input probabilistic pulse train. The device generally comprises an up/down counter and a comparator. The up/down counter keeps track of the difference between the number of input pulses and the number of output pulses. The comparator produces output pulses, generally with the probability of pulses being generated positively related to the value of the difference.

Abstract: A Neural Network using interconnecting weights each with two values, one of which is selected for use, can be taught to map a set of input vectors to a set of output vectors.A set of input vectors is applied to the network and in response, a set of output vectors is produced by the network. The error is the difference between desired outputs and actual outputs.The network is trained in the following manner. A set of input vectors is presented to the network, each vector being propogated forward through the network to produce an output vector. A set of error vectors is then presented to the network and propagated backwards. Each Tensor Weight Element includes a selective change means which accumulates particular information about the error.After all the input vectors are presented, an update phase is initiated.

Abstract: Pulse trains are utilized for the transmission of information in a neural network. A squash function is achieved by logically OR'ing together pulsed outputs, giving f(x) approximately 1-e.sup.-x. For Back Propagation, as derived by Rumelhart, the derivative of the squash function is available by examining the time when no OR'ed together pulses are present, being 1-f(x), or e.sup.-x. Logically AND'ing of the two signals. Mulitplication of input frequencies by weights is accomplished by modulating the width of the output pulses, while keeping the frequency the same.