Other

Agfa Corporation

Agfa Division, Bayer Corporation

David L Cooper

Philip A Rombult

Robert S Ring

James C Folsom

Laurence S Blake

Ross A Freeman

Roger A Jacques

Gerald L Smith

Chang J Yee

Pedro Beildeck

Ronald W Krohn

Jerry F Negrotti

Fractal computers are neural network architectures that exploit the characteristics of fractal attractors to perform general computation. This disclosure explains neural network implementations for each of the critical components of computation: composition, minimalization, and recursion. It then describes the creation of fractal attractors within these implementations by means of selective amplification or inhibition of input signals, and it describes how to estimate critical parameters for each implementation by using results from studies of fractal percolation. These implementation provide standardizable implicit alternatives to traditional neural network designs. Consequently, fractal computers permit the exploitation of alternative technologies for computation based on dynamic systems with underlying fractal attractors.

Method and apparatus for fractal computation

A method and apparatus for using a neural network to process information includes multiple nodes arrayed in multiple layers for transforming input arrays from prior layers or the environment into output arrays for subsequent layers or output devices. Learning rules based on reinforcement are applied. Interconnections between nodes are provided in a manner whereby the number and structure of the interconnections are self-adjusted by the learning rules during learning. At least one of the layers is used as a processing layer, and multiple lateral inputs to each node of each processing layer are used to retrieve information. The invention provides rapid, unsupervised processing of complex data sets, such as imagery or continuous human speech, and captures successful processing or pattern classification constellations for implementation in other networks. The invention includes application-specific self-adjusting multi-layer architectures that employ reinforcement learning rules to create updated data arrays for computation.

Self-adjusting multi-layer neural network architectures and methods therefor

A semantic attractor memory uses an evolving neural network architecture and learning rules derived from the study of human language acquisition and change to store, process and retrieve information. The architecture is based on multiple layer channels, with random connections from one layer to the next. One or more layers are devoted to processing input information. At least one processing layer is provided. One or more layers are devoted to processing outputs and feedback is provided from the outputs back to the processing layer or layers. Inputs from parallel channels are also provided to the one or more processing layers. With the exception of the feedback loop and central processing layers, the network is feedforward unless it is employed in a hybrid back-propagation configuration. The learning rules are based on non-stationary statistical processes, such as the Polya process or the processes leading to Bose-Einstein statistics, again derived from considerations of human language acquisition. The invention provides rapid, unsupervised processing of complex data sets, such as imagery or continuous human speech, and a means to capture successful processing or pattern classification constellations for implementation in other networks.

Method and apparatus for neural networking using semantic attractor architecture

An imagesetting or platesetting system and method for transporting one or more sheets of media having varying stiffness and thickness includes the steps of: transporting the sheets through the system in a first direction (A); recording an image onto the sheets; and redirecting one or more of the sheets in a transverse direction (B) relative to the first direction (A). Preferably, this is accomplished using: a transport mechanism for transporting the sheets of media through the system in the first direction (A); an imager for recording the image onto the sheets; and a jogging mechanism for redirecting the sheets in the transverse direction (B). The jogging mechanism can be integrated or modular to the system. Moreover, the jogging mechanism can be used in both internal and external drum imagers.

Redirecting printing media in a prepress printing environment

Method and apparatus for neural networking using semantic attractor

The primary function of the optional handler is to make plates available on demand to the imaging engine. A multitude of plates are stored inside cassettes and these cassettes are loaded into the handler. There may be up to four cassettes residing in the handler. Inside a cassette there may be a protective interleaf sheet, sometimes called a slip sheet, between each plate which is removed by the handler and discarded. The handler receives commands from the engine control sequencer which provides instructions as to what cassette needs to be accessed to make a plate available to the picker mechanism so the plate may be conveyed to the imaging engine. Conversely the handler provides status information to the engine to make full interaction with the system possible.

Cassette for storing and accessing plates within an automated plate

A roller is provided with a clamping mechanism that clamps into a closed position upon rotation of the roller in a winding direction, and unclamps into an open position upon rotation in an unwind direction. The roller has a split-core comprising two hollow, semicircular, core halves that toggle between the clamped and unclamped positions when pivoted about a pivot point that is concentric with the rotational axis of the roller. A snap-pivot mechanism provides a snap-action between the core halves by a leaf spring positioned between the core halves. The rotationally free core half is maintained in a fixed position by a pivoting retractable spring plunger engaging a tab on the core half, while the driven core half is rotated toward the fixed free core half, causing the leaf spring to snap to an over center position and clamp the core halves together.

Growing community of inventors

Fairfax Station, VA, United States of America

David L Cooper