International Business Machines Corporation

Ghislain Imbert De Tremiolles

Pascal R Tannhof

Fernando Incertis Carro

Didier R Louis

Philippe Klein

Rita Asuncion Jarillo Sanchez, Legal Representative

A method and system for persistently linking sources to text copied from the sources. A first electronic document and first text appearing in the first electronic document are displayed. Selected text and an address of a source electronic document that includes the selected text are obtained from a web page differing from the first electronic document. A temporary computer object is generated to include: a header, the obtained address of the source electronic document in the header, and the obtained selected text. The header includes an identifier of the temporary computer object and an attribute pertaining to the address of the source electronic document. The selected text in the temporary computer object is persistently linked with the source electronic document via the address of the source electronic document in the temporary computer object. The temporary computer object is stored in the first electronic document after the first text.

Linking sources to copied text

A method and system for processing electronic documents. A temporary computer object is created. An address of a first electronic document is obtained. A first tag, a second tag, and the address of the first electronic document are copied into a header of the created temporary computer object. Selected text from the first electronic document is obtained. The first and second tag respectively mark the beginning and the end of the header. The address of the first electronic document is disposed between the first and second tags. The selected text and a third tag are copied into the created temporary computer object. The third tag marks the end of the created temporary computer object. The selected text is disposed between the header of the created temporary computer object and the third tag. The created temporary computer object is stored in a second electronic document.

A method and systems for copying textual objects from source documents into an object document, and for tagging, linking and processing said copied textual portions, including the disclosure of a new type of hyperlinking mechanism, for enabling to identify and trace the sources and the authorship of said copied textual portions or of all textual sub-portions or fragments of text that could be generated from said copied textual portions by editing the object document. The invention can be implemented by means of software implementing the disclosed system and method running on word-processors and web browsers.

Method and systems for linking sources to copied text

The method and circuits of the present invention aim to associate a complex component operator (CC_op) to each component of an input pattern presented to an input space mapping algorithm based artificial neural network (ANN) during the distance evaluation process. A complex operator consists in the description of a function and a set of parameters attached thereto. The function is a mathematical entity (either a logic operator e.g. match(Ai,Bi), abs(Ai&#x2212;Bi), . . . or an arithmetic operator, e.g. &#x3e;, &#x3c;, . . . ) or a set of software instructions possibly with a condition. In a first embodiment, the ANN is provided with a global memory, common for all the neurons of the ANN, that stores all the CC_ops. In another embodiment, the set of CC_ops is stored in the prototype memory of the neuron, so that the global memory is no longer physically necessary. According to the present invention, a component of a stored prototype may now designate objects of different nature. In addition, either implementation significantly reduces the number of components that are required in the neurons, therefore saving room when the ANN is integrated in a silicon chip.

Method and circuits for associating a complex operator to each component of an input pattern presented to an artificial neural network

An artificial neural network (ANN) based system that is adapted to process an input pattern to generate an output pattern related thereto having a different number of components than the input pattern. The system () is comprised of an ANN () and a memory (), such as a DRAM memory, that are serially connected. The input pattern () is applied to a processor (), where it can be processed or not (the most general case), before it is applied to the ANN and stored therein as a prototype (if learned). A category is associated with each stored prototype. The processor computes the coefficients that allow the determination of the estimated values of the output pattern, these coefficients are the components of a so-called intermediate pattern (). Assuming the ANN has already learned a number of input patterns, when a new input pattern is presented to the ANN in the recognition phase, the category of the closest prototype is output therefrom and is used as a pointer to the memory. In turn, the memory outputs the corresponding intermediate pattern. The input pattern and the intermediate pattern are applied to the processor to construct the output pattern () using the coefficients. Typically, the input pattern is a block of pixels in the field of scaling images.

System for scaling images using neural networks

Method and circuits for scaling images using neural networks

An improved Artificial Neural Network (ANN) is disclosed that comprises a conventional ANN, a database block, and a compare and update circuit. The conventional ANN is formed by a plurality of neurons, each neuron having a prototype memory dedicated to store a prototype and a distance evaluator to evaluate the distance between the input pattern presented to the ANN and the prototype stored therein. The database block has: all the prototypes arranged in slices, each slice being capable to store up to a maximum number of prototypes; the input patterns or queries to be presented to the ANN; and the distances resulting of the evaluation performed during the recognition/classification phase. The compare and update circuit compares the distance with the distance previously found for the same input pattern updates or not the distance previously stored.

Method and circuits to virtually increase the number of prototypes in artificial neural networks

Let us consider a plurality of input patterns having an essential characteristic in common but which differ on at least one parameter (this parameter modifies the input pattern in some extent but not this essential characteristic for a specific application). During the learning phase, each input pattern is normalized in a normalizer, before it is presented to a classifier. If not recognized, it is learned, i.e. the normalized pattern is stored in the classifier as a prototype with its category associated thereto. From a predetermined reference value of that parameter, the normalizer computes an element related to said parameter which allows to set the normalized pattern from the input pattern and vice versa to retrieve the input pattern from the normalized pattern. As a result, all these input patterns are represented by the same normalized pattern. The above method and circuits allow to reduce the number of required prototypes in the classifier, improving thereby its response quality.

Method and circuits for encoding an input pattern using a normalizer and a classifier

A method is described to improve the data transfer rate between a personal computer or a host computer and a neural network implemented in hardware by merging a plurality of input patterns into a single input pattern configured to globally represent the set of input patterns. A base consolidated vector (U'*) representing the input pattern is defined to describe all the vectors (U, . . . , U) representing the input patterns derived thereof (U&#x2032;, . . . , U&#x2032;) by combining components having fixed and 'don't care' values. The base consolidated vector is provided only once with all the components of the vectors. An artificial neural network (ANN) is then configured as a combination of sub-networks operating in parallel. In order to compute the distances with an adequate number of components, the prototypes are to include also components having a definite value and 'don't care' conditions. During the learning phase, the consolidated vectors are stored as prototypes. During the recognition phase, when a new base consolidated vector is provided to ANN, each sub-network analyses a portion thereof After computing all the distances, they are sorted one sub-network at a time to obtain the distances associated to each vector.

Method to improve the data transfer rate between a computer and a neural network

The method and circuits of the present invention aim to associate a norm to each component of an input pattern presented to an input space mapping algorithm based artificial neural network (ANN) during the distance evaluation process. The set of norms, referred to as the &ldquo;component&rdquo; norms is memorized in specific memorization means in the ANN. In a first embodiment, the ANN is provided with a global memory, common for all the neurons of the ANN, that memorizes all the component norms. For each component of the input pattern, all the neurons perform the elementary (or partial) distance calculation with the corresponding prototype components stored therein during the distance evaluation process using the associated component norm. The distance elementary calculations are then combined using a &ldquo;distance&rdquo; norm to determine the final distance between the input pattern and the prototypes stored in the neurons. In another embodiment, the set of component norms is memorized in the neurons themselves in the prototype memorization means, so that the global memory is no longer physically necessary. This implementation allows to significantly optimize the consumed silicon area when the ANN is integrated in a silicon chip.

Method and circuits for associating a norm to each component of an input pattern presented to a neural network

In the search of the minimum value among a set of p Numbers coded on q bits, each Number is split into K sub-values coded on n bits (q>&equals;K&times;n). Parameter K thus assigns a rank to each sub-value so that K slices of bits are formed wherein each slice is composed of sub-values of the same rank. Each sub-value is then encoded on m bits (m>n) using a &ldquo;thermometric&rdquo; coding technique. A parallel search is then performed on the first slice of encoded sub-values (MSBs) to determine the minimum sub-value of that slice. All the Numbers associated to sub-values that are greater than the minimum sub-value that has been evaluated are deselected. The evaluation process is continued the same way until the last slice (LSBs) has been processed. At the end of the evaluation process, the Number which remains selected has the minimum value. The response time (i.e. the number of processing steps) now only depends upon the number K of sub-values in which the Numbers have been split up. The method applies to search the maximum as well.

Method and circuits for performing the quick search of the minimum/maximum value among a set of numbers

A system for accessing a memory organized in memorization subsystems or memory blocks, e.g. standard Dual In-line Memory Modules, wherein the words to be stored are split into unitary elements so that several memorization subsystems are used to store one word and its associated Block Error Code (BEC) bits, is disclosed. The system includes a detector to detect a failure within a memorization subsystem. Insulator that are associated to each memorization subsystem insulate the failed memory block, and a new memorization subsystem is accessed in lieu of the failed one thanks to identification device which determine an available unfailed memory block. The user may replace the failed memory block without shutting down the memory device.

Memory access system

The improved neural network of the present invention results from the combination of a dedicated logic block with a conventional neural network based upon a mapping of the input space usually employed to classify an input data by computing the distance between said input data and prototypes memorized therein. The improved neural network is able to classify an input data, for instance, represented by a vector A even when some of its components are noisy or unknown during either the learning or the recognition phase. To that end, influence fields of various and different shapes are created for each neuron of the conventional neural network. The logic block transforms at least some of the n components (A1, . . . , An) of the input vector A into the m components (V1, . . . , Vm) of a network input vector V according to a linear or non-linear transform function F. In turn, vector V is applied as the input data to said conventional neural network. The transform function F is such that certain components of vector V are not modified, e.g. Vk&equals;Aj, while other components are transformed as mentioned above, e.g. Vi&equals;Fi(A1, . . . , An). In addition, one (or more) component of vector V can be used to compensate an offset that is present in the distance evaluation of vector V. Because, the logic block is placed in front of the said conventional neural network any modification thereof is avoided.

Growing community of inventors

Paris, France

Ghislain Imbert De Tremiolles