King's College London

University College London

British Telecommunications Public Limited Company

British Telecommunications Corporation

John G Taylor

Trevor G Clarkson

Behnam Azvine

Neill R Taylor

Denise Gorse

Nader Azarmi

Kwok Ching Tsui

David Djian

Kwok C Tsui

David P Djian

Apparatus for generating sequences of elements including at least one task unit, each of which has an upper and a lower neural network connected in a hierarchical relationship and is operable to output a sequence of elements. Each of the upper and lower neural networks is a class of temporal neural networks having an infinite number of internal states.

Sequence generator

An apparatus and operating method for generating a second one or more sequences of elements after receiving a first one or more sequence of elements. The apparatus includes an identifying device that receives a first one or more sequence of elements, accesses stored sequences, and identifies which of the stored sequences each of the first one or more received sequences of elements most closely resembles. The identifying device is operable to output for each received sequence of elements, an identifying signal indicative of the correspondingly identified stored sequence. The apparatus further includes a sequence generator that generates sequences of elements, operates to receive an input, an identifying signal, and generates a sequence of elements in response thereto.

Apparatus for generating sequences of elements

Devices for use in neural processing

Neural processing devices for handling real-valued inputs

A neuron for use in a neural processing network, comprises a memory having a plurality of storage locations at each of which a number representing a probability is stored, each of the storage locations being selectively addressable to cause the contents of the location to be read to an input of a comparator. A noise generator inputs to the comparator a random number representing noise. At an output of the comparator an output signal appears having a first or second value depending on the values of the numbers received from the addressed storage location and the noise generator, the probability of the output signal having a given one of the first and second values being determined by the number at the addressed location. Preferably the neuron receives from the environment signals representing success or failure of the network, the value of the number stored at the addressed location being changed in such a way as to increase the probability of the successful action if a success signal is received, and to decrease the probability of the unsuccessful action if a failure signal is received.

Digital artificial neuron based on a probabilistic ram

Growing community of inventors

London, United Kingdom

John G Taylor