Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for displaying augmented reality content. The program and method provide for causing, by a messaging application running on a device, a camera of the device to capture an image; receiving by the messaging application, speech input to select augmented reality content for display with the image; determining at least one keyword included in the speech input; determining that the at least one keyword indicates an object depicted in the image and an action to perform with respect to the object; identifying, from plural augmented reality content items, an augmented reality content item that corresponds to performing the action with respect to the object; and displaying the augmented reality content item with the image.

Abstract: Systems and methods are provided for providing an augmented reality experience. The systems and methods perform operations comprising: generating, for display by a messaging application, an image comprising one or more augmented reality elements, the one or more augmented reality elements being associated with a configurable entity; receiving, by the messaging application, speech input from a user; determining a schema associated with the one or more augmented reality elements; causing the speech input to be processed by a speech understanding model in accordance with the schema to determine one or more configurable state entity update values; updating the configurable entity associated with the one or more augmented reality elements based on the one or more configurable state entity update values; and modifying the one or more augmented reality elements in the image based on the updated configurable entity.

Abstract: Disclosed herein are systems and methods for establishing a metadata exchange channel between a media playback system and a networked microphone system, wherein the networked microphone system comprises a networked microphone device and a networked microphone server. After establishing the metadata exchange channel, the media playback system experiences a metadata exchange triggering event. In response to experiencing the metadata exchange triggering event, the media playback system provides metadata to the networked microphone system via the metadata exchange channel.

Abstract: Methods, apparatus, and processor-readable storage media for a neural network-based message communication framework with summarization and on-demand audio output generation are provided herein.

Abstract: An input assistance system includes a terminal device including a display screen, an acquisition unit, a recognition unit, an input item display unit, a recognition result display unit, and a reception unit. The acquisition unit acquires utterance voice data of a user. The recognition unit performs voice recognition of the utterance voice data to generate text data. The input item display unit displays a plurality of input items including the input item associated with the text data. The recognition result display unit displays the text data. The reception unit accepts an operation of selecting the input item associated with the text data displayed by the recognition result display unit from the plurality of input items displayed by the input item display unit. The reception unit accepts the operation of selecting the input item associated with the text data when the plurality of input items and the text data are displayed.

Abstract: Techniques for providing a unique UI and backend service designed to improve item placement within a defined environment are described. The placement of an item within the UI is governed by rules. Measurement data detailing dimensions of an area is received. An item selection menu within the UI is populated with items in a database. A design layout area, which represents the measured area, is displayed. In response to an item being selected from the item selection menu and being placed at a location within the design layout area, a set of rules is triggered. The placement of the item either does not violate the rules or, alternatively, that placement does violate the set rules. If the rules are violated, then alternative suggestions are provided. If the rules are not violated, then the item is placed at the location.

Abstract: A Rapid Aero Modeling program and process may be applied to computational experiments such as computational fluid dynamics (CFD) programs to obtain aerodynamic models which may be in the form of polynomial equations. The program and process may be utilized to estimate (develop) aerodynamic models appropriate for flight dynamics studies, simulations, and the like. Feedback loops are provided around computational codes to rapidly guide testing toward aerodynamic models that meet user-defined fidelity criteria. A user has the freedom to choose a specific level of fidelity in terms of prediction error, in advance of a CFD test (computation).

Abstract: A system and a method for determining a sealant profile to be applied by a sealant applicator, the applicator being arranged to apply sealant to the surface of a component. The system includes an imager configured to generate measurement data representing the surface of the component and a data receiver. The data receiver is arranged to receive the generated measurement data and predetermined component-related data. The system also includes a processor arranged to analyse the received data and to generate, based on the analysis, a sealant profile for application to the component, and a data output arranged to output data representing the generated sealant profile to the sealant applicator.

Abstract: A computer-implemented method of modelling a hydraulic network comprising pipes and pressure monitoring points, the method comprising: creating a model comprising a plurality of nodes and a plurality of edges connecting the nodes; wherein each node represents a pressure monitoring point within the hydraulic network, and each edge connects two nodes and represents an amalgamation of the pipes of the network that span between the pressure monitoring points represented by the two nodes.

Abstract: Systems and methods for synchronizing programs for simulation of a technical system. The programs including a first simulation program and a second simulation program. The first simulation program simulates the kinematics of the technical system and the second simulation program simulates a control of the operation of the technical system. The first simulation program outputs values of a first variable at first-time points between first-time intervals according to a first frequency in virtual simulated time and the second simulation program outputs values of a second variable at second time points between second time intervals according to a second frequency in virtual simulated time, the first frequency being lower than the second frequency.

Abstract: A repository is configured in a hybrid data processing environment comprising a classical computing system and a quantum computing system, to hold a plurality of quantum circuit components (QCC(s)). A degree of difficulty in simulating the received QCC in the classical computing system is transformed into a classical hardness score. A degree of difficulty in implementing the received QCC in the quantum computing system is transformed into a quantum hardness score. A first parameter in a metadata data structure associated with the received QCC is populated with the classical hardness score. A second parameter in the metadata data structure associated with the received QCC is populated with the quantum hardness score. The received QCC is transformed into a library element by at least augmenting the received QCC with the metadata data structure. The library element is added to the repository.

Abstract: Disclosed is a method for identifying fragile lines in power grid based on electrical betweenness, which comprises the following steps: constructing the power grid into a network diagram, sequentially removing lines in the network diagram, and sorting the electrical betweenness of each line from large to small; constructing a nonlinear model of complex network cascade failure considering overload and weighted edges, and respectively performing two ways of removing lines for sorted electrical betweenness, namely sequentially removing preset proportion lines and sequentially removing all lines until no new lines are removed in the network diagram; obtaining a change of generator-load power before and after each line removal, and evaluating a severity of power grid failure based on the change of generator-load power, thus completing an identification of power grid fragile lines.

Abstract: Method for quantitative flow analysis of a tree of conduits perfusing an organ from at least two bi-dimensional images, the method comprising the following steps: a) making a 3D reconstruction of at least part of the tree from said at least two bi-dimensional images; b) identifying a segment of interest within the 3D reconstruction either automatically or semi-automatically upon user input; c) making calculations based on the 3D reconstruction to determine geometrical features of the conduits such as diameters, lengths, curvatures, centrelines or the like; d) receiving indication from the user to input a multi-scale functional model of the tree to be considered for the flow analysis and to input the location of the segment of interest within such model; e) adjusting the part of the functional model related to the segment of interest using geometrical features of the 3D reconstruction; f) performing quantitative flow analysis based on the functional model so obtained.

Abstract: A method for verifying an integrated circuit (IC) design described in a hardware description or hardware verification language (HDHVL) is provided. The method includes identifying connections between random variables and coverage areas of the IC design, as described in HDHVL code, the connections being identified by determining which coverage areas of the IC design will be influenced during simulation by which random variables. The method can further include storing the identified connections in a database, and using, by a processor, connections retrieved from the database to simulate and verify the coverage areas of the IC design.

Abstract: A semiconductor device includes: M*1st conductors in a first layer of metallization (M*1st layer) and being aligned correspondingly along different corresponding ones of alpha tracks and representing corresponding inputs of a cell region in the semiconductor device; and M*2nd conductors in a second layer of metallization (M*2nd layer) aligned correspondingly along beta tracks, and the M*2nd conductors including at least one power grid (PG) segment and one or more of an output pin or a routing segment; and each of first and second ones of the input pins having a length sufficient to accommodate at most two access points; each of the access points of the first and second input pins being aligned to a corresponding different one of first to fourth beta tracks; and the PG segment being aligned with one of the first to fourth beta tracks.

Abstract: One or more line ends of a putative integrated circuit design are modelled using a constraint graph. A longest path algorithm is applied on subgraphs of the constraint graph. An extent minimization algorithm is carried out on the subgraphs of the constraint graph and routing on the putative integrated circuit design is carried out based on results of the longest path algorithm and the extent minimization algorithm.

Abstract: To increase the efficiency of electronic design automation, at an end point of physical design synthesis optimization flow for a putative integrated circuit design having a plurality of nets, identify at least one congested region in the putative integrated circuit design. Identify those of the nets of the putative integrated circuit design traversing through the at least one congested region, to obtain a plurality of candidate nets for demotion. Demote a plurality of selected nets, selected from the plurality of candidate nets for demotion, from an upper routing layer of the putative integrated circuit design to a lower routing layer of the putative integrated circuit design. At least some of the plurality of selected nets experience a loss of timing quality of result after the demoting.

Abstract: A machine learning-based process includes identifying a first set of features that includes features of a reference implementation of a circuit design and features of a synthesized version of a modified version of the circuit design. A first classification model is applied to the first set of features, and the first classification model indicates a full implementation flow or an incremental implementation flow. The full implementation flow is performed on the synthesized version of the modified version in response to the first classification model indicating the full implementation flow, and the incremental implementation flow is performed on the synthesized version of the modified version in response to the first classification model indicating the incremental implementation flow. The full and incremental implementation flows generate implementation data that is suitable for making an integrated circuit (IC).

Abstract: A method of fabricating an integrated circuit includes placing a first set of conductive feature patterns on a first level, placing a second set of conductive feature patterns on a second level, placing a first set of via patterns between the second set of conductive feature patterns and the first set of conductive feature patterns, placing a third set of conductive feature patterns on a third level different from the first level and the second level, placing a second set of via patterns between the third set of conductive feature patterns and the second set of conductive feature patterns, and manufacturing the integrated circuit based on at least one of the above patterns of the integrated circuit.

Abstract: Embodiments of the application disclose a check tool and a check method for a Design Rule Check (DRC) rule deck of an integrated circuit layout. The check tool (100) for the DRC rule deck of the integrated circuit layout includes: an intelligent database creation engine (110), configured to generate a test case database; an intelligent arrangement engine (120), configured to generate a standard integrated circuit layout (150) according to the test case database; and an intelligent detection and analysis engine (130), configured to detect and analyze a target DRC rule deck (140) of the integrated circuit layout according to the standard integrated circuit layout (150).

Abstract: The present disclosure relates to software-defined methods and apparatuses for designing a wafer-level switching system, including: determining wafer-level switching system layout constraints; constructing a target wafer-level switching system and determining parameters, and designing a logical topology of a switching network; designing a layout of the switching chiplets on the wafer substrate; respectively designing interface structures of external chiplets and internal chiplets; configuring a switching mode and an enable state of each port of the switching chiplets; ending the process when the target logical topology can be achieved by the wafer-level switching system; otherwise, reconstructing a logical topology of a switching network and mapping it to the substrate.

Abstract: A system and method for converting a document is described. The system accesses a document comprising one or more section breaks. The system detects sections of the text document demarked by the one or more section breaks and generates a section title metadata and a section summary metadata for each section of the plurality of sections. The system inserts the section title metadata and the section summary metadata at the corresponding section breaks in the text document. The system modifies the text document into slides. Each slide being formed for each section based on the corresponding section title metadata and the section summary metadata. The system generates a presentation document based on the slides.

Abstract: The automated generation of a web site preview based on a web site identifier, where the web site preview has one or more controls that facilitate connection to one or more endpoints. In response to receiving the web site identifier from the client computing system, the service uses the web site identifier to navigate to the web site identified by the web site identifier. After navigating to that web site, the service accesses an action identifier and an associated endpoint identifier from the web site. The service then generates preview data representing a preview of the web site represented by the web site identifier. The service provides the preview data to the client, where the preview with the control is rendered, so as to facilitate connection with the associated endpoint of the control.

Abstract: Disclosed are methods, apparatus, systems, and computer readable storage media for interacting with one or more data objects in an online social network. A user interface includes a publisher with a custom action. The custom action is defined in accordance with custom action instructions provided by a first entity via an application programming interface (API). Such custom action instructions may declaratively or programmatically define the data object, the interaction to be performed with the data object, and other attributes associated with the custom action. A user may request to interact with the data object via selection of the custom action by a second entity. Information may be submitted through the publisher to interact with the data object to update a database system associated with the data object. A feed item may be presented for inclusion in the information feed based on the update.

Abstract: Systems and methods for configuring a medical record generation platform are provided. A first graphical user interface comprising a visual representation of a natural-language statement structure is displayed, and a first input comprising an instruction to update the natural-language statement structure to specify a first aspect of patient medical information is received. In response to receiving the first input, display of the visual representation is updated to include a visual representation of the first aspect of patient medical information, and an option group region representing a set of options for describing the first aspect is displayed. In accordance with the first user input, a data structure is stored comprising instructions for providing a platform for generating a natural-language healthcare document conforming to the natural-language statement structure represented by the visual representation, wherein the natural-language statement specifies the first aspect of patient medical information.

Abstract: Described herein are techniques for automatically updating (e.g., augmenting) the content of documents with additional content. Such documents may be generated automatically using a natural language generation (NLG) engine. In some embodiments, the techniques developed by the inventors are configured to update a document with text explaining what caused a certain event or set of events described in the document. The techniques developed by the inventors involve multiple acts. For example, the techniques may identify content of relevance to a document, may identify whether the content includes a text segments having a causal structure, and may separate the cause sub-segment from the cause-segment. The cause sub-segment, and optionally the effect sub-segment, may be used to update the document.

Abstract: A document creation assistance apparatus includes a tree structure generation unit configured to analyze a learning document for system development and generate a tree structure representing separate sections of the learning document, a frequency calculation unit configured to calculate, per leaf node of the tree structure, a frequency vector of a word that appears, a question extraction unit configured to extract, according to the frequency vector, a word about which a user is to be questioned, a question presentation unit configured to present a question about the extracted word to the user and receive an answer, and a document generation unit configured to generate a document with the extracted word and the answer set in a section of the separate sections of the leaf node according to the separate sections of the tree structure.

Abstract: Disclosed herein are methods, systems, and computer-readable media for automatically generating and editing text. In an embodiment, a method may include receiving an input text prompt and receiving one or more user instructions. The method may also include accessing a language model based on the input text prompt and the one or more user instructions. The method may also include outputting, using the accessed language model, language model output text. The method may also include editing the input text prompt based on the language model and the one or more user instructions by replacing at least a portion of the input text prompt with the language model output text.

Abstract: A method and computer system are provided for generating a text summary. An input text is processed by a model that comprises a set of attention heads. The model is trained to generate abstractive summaries of text documents. A subset of the attention heads are identified. For each attention head in the subset, a portion is identified from the input text that is used to generate the abstractive summary. For each sentence of the input text, a fractional size is calculated for an intersection of the portion and the respective sentence relative to the respective sentence. A subset of the sentences is then determined, where the respective fractional size of each sentence in the subset meets a first threshold. An extractive summary of the input text is then generated from the subset of sentences.

Abstract: A computer-implemented method includes: allowing a user of a spreadsheet program to select a transaction from a list of transactions for a transaction management platform; creating a mapping sheet in a workbook of the spreadsheet program, the mapping sheet listing, in a first column, data fields associated with the selected transaction; receiving, in a second column of mapping sheet, references to cells of the workbook that correspond to the data fields in the first column; and using the mapping sheet to automatically update the data fields associated with the selected transaction with data values from the corresponding cells of the workbook in response to a user command.

Abstract: Systems, computer program products, and methods are described herein for providing a platform for generating published reports using report and worksheet building with position mapping identification. The present invention is configured to establish a reporting and analytics platform for a user interface and receive, from the user interface, a single-selection input referencing a set of system identification values associated with a first set of data in the reporting and analytics platform. The system may then display a plurality of formatting options for the set of system identification values on the user interface. The system can assign a selected formatting option to the system identification values and apply the selected formatting option to the first set of data in the reporting and analytics platform. The selected formatting options can be applied to additional sets of data based on system identification values.

Abstract: Embodiments of the disclosure provide a multi-class classification system. An exemplary system includes at least one processor and at least one non-transitory memory storing instructions that, when executed by the at least one processor, cause the system to perform operations. The operation includes applying a multi-class classifier to classify a set of objects into multiple classes and applying a plurality of binary classifiers to the set of objects, wherein the plurality of binary classifiers are decomposed from the multi-class classifier, each binary classifier classifying the set of the objects into a first group consisting of one or more classes selected from the multiple classes and a second group consisting of one or more remaining classes of the multiple classes. The operation also includes jointly classifying the set of objects using the multi-class classifier and the plurality of binary classifiers.

Abstract: A data processing method includes: obtaining a to-be-detected text, and determining a context word set and a candidate substitute word set corresponding to a to-be-detected word in the to-be-detected text to be inputted into a pronoun resolution neural network for feature extraction; performing positive-example iteration processing and negative-example iteration processing on the features corresponding to the context word set and the candidate substitute word set, to obtain a positive-example feature vector length and a negative-example feature vector length, and calculating a substitute probability corresponding to each candidate substitute word in the candidate substitute word set according to the positive-example feature vector length and the negative-example feature vector length; determining a target substitute word according to the substitute probability corresponding to the each candidate substitute word; and inserting the target substitute word into the to-be-detected text according to a position corr

Abstract: An apparatus and method for dynamic data synthesis wherein the apparatus receives a first textual data set, displays at least an interface field, populates the at least an interface field with at least an element of the first textual data set, generates a destination-formatted query using the populated at least an interface field, transmits the formatted query to a remote device, receives a second textual data set, outputs a user score and a set of score metadata, generates a comprehensive report, and displays the comprehensive report to the user.

Abstract: An evaluation device includes a first calculation unit configured to calculate feature quantities of respective words, the feature quantities corresponding to text data in which a target of any goal of the SDGs is described and text data in which an outline of one or more first services for which a contribution to the goal that is clear is described, a generation unit configured to generate a sentence feature matrix based on the feature quantities of the respective words, a second calculation unit configured to calculate, when text data in which an outline of a second service is described is input, feature quantities of respective words, and an evaluation unit configured to evaluate a degree of a contribution of the second service to the goal based on the feature quantities of the respective words relevant to the second service and the sentence feature matrix.

Abstract: A method including transcribing, automatically, an ongoing stream of voice data into text phrases. The method also includes receiving an indication of a selected text phrase in the text phrases. The method also includes converting the selected text phrase to a selected phrase vector. The method also includes generating a subsequent text phrase, after the selected text phrase, from the ongoing stream of voice data, and adding the subsequent text phrase to the text phrases. The method also includes converting the subsequent text phrase to a subsequent phrase vector. The method also includes generating a similarity confidence score from the selected phrase vector and the subsequent phrase vector, using a machine learning model. The method also includes highlighting, responsive to the similarity confidence score exceeding a threshold value, the subsequent text phrase in the text phrases.

Abstract: Privacy, protection, and de-anonymization are issues of societal importance that are implicitly at the core of several key information systems, from electronic health records to online reviews. The system and method herein allows for an identification of an author of anonymous writing based on the text and structured data, subject to practical constraints on the intruder's amount of training data and effort using Shapley values.

Abstract: A system and method for natural language processing for document sequences comprises a computing device configured to train a neural network as a function of a corpus of documents, wherein training comprises receiving the corpus of documents, identifying significant terms, and tuning, as a function of the corpus of documents, the neural network to generate a plurality of vectors for each significant term of the plurality of significant terms, a vector in a vector space representing semantic relationships between the significant terms and semantic units in the corpus of documents, receive a current document sequence including a plurality of documents in a sequential order, map a plurality of mapped terms of the plurality of significant terms to the plurality of documents as a function of the neural network and the plurality of vectors, and generate a plurality of timelines as a function of the sequential order and the mapped terms.

Abstract: At least one processing device, operating upon a body of text in a document, identifies occurrences of at least one content type in the body of text. The at least one processing device thereafter generates a user interface that includes portions of text from the body of text that are representative of at least some of the occurrences of the at least one content type in the document. For each content type, the occurrences corresponding to that content type can be grouped together to provide grouped content type occurrences that are subsequently collocated in the user interface. Those portions of text corresponding to the grouped content type occurrences may be arranged in alphanumeric order. The user interface may comprise at least a portion of the body of text as well as indicia indicating instances of the occurrences within the portion of the body of text.

Abstract: At a terminal equipment side, sentence information received by the terminal equipment is acquired. A part-of-speech label sequence of text data in the sentence information for which part-of-speech labelling is to be performed is extracted. A detection result is acquired by detecting legitimacy of the part-of-speech label sequence. When the detection result indicates that the part-of-speech label sequence is illegitimate, the part-of-speech label sequence is corrected. A corrected part-of-speech label sequence is output as a result of performing part-of-speech labelling on the text data. Semantics corresponding to the sentence information is determined according to output sentence information with part-of-speech labels.

Abstract: The present invention relates to an apparatus and method for automatically generating machine reading comprehension training data, and more particularly, to an apparatus and method for automatically generating and managing machine reading comprehension training data based on text semantic analysis. The apparatus for automatically generating machine reading comprehension training data according to the present invention includes a domain selection text collection unit configured to collect pieces of text data according to domains and subjects, a paragraph selection unit configured to select a paragraph using the pieces of collected text data and determine whether questions and correct answers are generatable, and a question and correct answer generation unit configured to generate questions and correct answers from the selected paragraph.

Abstract: The example embodiments are directed toward improvements in document classification. In an embodiment, a method is disclosed comprising generating a set of sentences based on a document; predicting a set of labels for each sentence using a multi-label classifier, the multi-label classifier including a self-attended contextual word embedding backbone layer, a bank of trainable unigram convolutions, a bank of trainable bigram convolutions, and a fully connected layer the multi-label classifier trained using a weakly labeled data set; and labeling the document based on the set of labels. The various embodiments can target multiple use cases such as identifying related entities, trending related entities, creating ephemeral timeline of entities, and others using a single solution. Further, the various embodiments provide a weakly supervised framework to train a model when a labeled golden set does not contain a sufficient number of examples.

Abstract: Artificial intelligence (AI) technology can be used in combination with composable communication goal statements to facilitate a user's ability to quickly structure story outlines in a manner usable by an NLG narrative generation system without any need for the user to directly author computer code. Narrative analytics that are linked to communication goal statements can employ a conditional outcome framework that allows the content and structure of resulting narratives to intelligently adapt as a function of the nature of the data under consideration. This AI technology permits NLG systems to determine the appropriate content for inclusion in a narrative story about a data set in a manner that will satisfy a desired communication goal.

Abstract: A computer implemented method for the automated analysis or use of data is implemented by a voice assistant. The method comprises the steps of: (a) storing in a memory a structured, machine-readable representation of data that conforms to a machine-readable language (‘machine representation’); the machine representation including representations of user speech or text input to a human/machine interface; and (b) automatically processing the machine representations to analyse the user speech or text input.

Abstract: A method for translating a source text of a first language to a second language. The method includes receiving a translation request including the source text in the first language; selecting, from the source text, at least a first segment, associating at least one first metadata parameter with the first segment; providing the first segment to a first translation memory for determining a first set of translation proposals; determining a first quality score for each translation proposal; and comparing the first quality score of each translation proposal with a first predetermined acceptance threshold, and wherein based on the comparison, when a first quality score of at least one translation proposal is greater than the first predetermined acceptance threshold, the method comprises selecting a given translation proposal and providing the given translation proposal as an accepted translation of the first segment and as at least a part of an accepted translation of the source text.

Abstract: Provided is a method of performing hybrid translation using a general-purpose neural network machine translator by a device, including: (a) receiving an original document configured of a first language from a user terminal; (b) determining a field of the original document by comparing the original document with a standard document for each field stored in a database; (c) generating a primary translation configured of a second language for the original document by using the general-purpose neural network machine translator; and (d) converting some expressions included in the primary translation into expressions in another second language with reference to a professional translation dictionary for the determined field to generate a secondary translation, wherein the expression includes any one of a word, a phrase, and a sentence.

Abstract: A differential multiplier-accumulator accepts A and B digital inputs plus a sign bit and generates a dot product P by applying the bits of the A input and the bits of the B inputs to respective positive and negative unit elements comprised of groups of AND gates coupled to charge transfer lines through a capacitor Cu. One of the positive and negative unit element is enabled by the sign bit, the enabled unit element receives one bit of the B input applied to all of the AND gates of the unit element, and each positive and negative unit element having the bits of A applied to each associated AND gate input of each unit element, which charge to charge transfer lines, and the charge transfer lines are coupled to binary weighted charge summing capacitors and to an analog to digital converter to generate a digital output product.

Abstract: A processing-in-memory (PIM) device includes a plurality of memory banks and a plurality of multiplication and accumulation (MAC) operators. The plurality of memory banks include a plurality of even memory banks and a plurality of odd memory banks. The plurality of MAC operators include a first MAC operator configured to be shared by a first even memory bank among the plurality of even memory banks and a first odd memory bank among the plurality of odd memory banks. The first MAC operator is configured to alternately perform an even MAC operation and an odd MAC operation.

Abstract: A floating-point accumulator circuit includes an addend input register having an addend exponent and an addend significand and an accumulation register with a first portion to hold a representation of an accumulation exponent and a second portion to hold a representation of an accumulation significand. A control circuit is also included to generate an accumulator zero control signal and an addend zero control signal based on the addend exponent and the accumulation exponent. It also includes an adder circuit with an output an input of the accumulation register. A first zeroing circuit sends either a zero or a value based on the addend significand to a first input of the adder circuit based on the addend zero control signal, and a second zeroing circuit sends either zeros or a value based on the accumulator significand to a second input of the adder circuit, based on the accumulator zero control signal.

Abstract: Apparatus for evaluating a mathematical function for a received input value includes a polynomial block configured to identify a domain interval containing the received input value over which the mathematical function can be evaluated, the mathematical function over the identified interval being approximated by a polynomial function; and evaluate the polynomial function for the received input value using a set of one or more stored values representing the polynomial function over the identified interval to calculate a first evaluation of the mathematical function for the received input value; and a CORDIC block for performing a CORDIC algorithm, configured to initialise the CORDIC algorithm using the first evaluation of the mathematical function for the received input value calculated by the polynomial block; and implement the CORDIC algorithm to calculate a refined evaluation of the mathematical function for the received input value.