Abstract: Sentiment analysis is a task in natural language processing. The embodiments are directed to using a generative language model to extract an aspect term, aspect category and their corresponding polarities. The generative language model may be trained as a single, joint, and multi-task model. The single-task generative language model determines a term polarity from the aspect term in the sentence or a category polarity from an aspect category in the sentence. The joint-task generative language model determines both the aspect term and the term polarity or the aspect category and the category polarity. The multi-task generative language model determines the aspect term, term polarity, aspect category and category polarity of the sentence.

Abstract: Technologies are provided for determining deficiencies in narrative textual data that may impact decision-making in a decisional context. A candidate text document and a reference corpus of text may be utilized to generate one or more topic models and document-term matrices, and then to determine a corresponding statistical perplexity and probabilistic coherence. Statistical determinations of a degree to which the candidate deviates from the reference normative corpus are determined, in terms of the statistical perplexity and probabilistic coherence of the candidate as compared to the reference. If the difference is statistically significant, a message may be reported to user, such as the author or an auditor of the candidate text document, so that the user has the opportunity to amend the candidate document so as to improve its adequacy for the decisional purposes in the context at hand.

Abstract: Provided is an electronic device for training a speech recognition model and a method for controlling thereof. The method of controlling the electronic device includes obtaining a first loss value by inputting a first learning speech sequence comprising an end-of-sentence (EOS) label to the speech recognition model; and training the speech recognition model based on the first loss value. Here, the first loss value is a loss value obtained from an output of an encoder included in the speech recognition model.

Abstract: A decision support system for assessing and reviewing large volume of digital content which comprise complex subject matter and providing recommendations on relevance of each content by applying context-based rules which are specific to the subject matter of interest. The rules are captured in a standardized format and the algorithm for the rules-based decision making is designed with the flexibility to select the rules based on the subject matter of interest.

Abstract: Method, apparatus, and non-transitory storage medium for neural network based dialogue generation, including receiving an input dialogue context, and generating queries based on the input dialogue context using a query generating neural network. The query generating neural network may be trained using a cheap noisy supervision function. The method may further include retrieving responses from a web-based search engine based on the generated queries, and generating dialogue based on the retrieved responses and the input dialogue context.

Abstract: A system for protecting personal data contained on an RFID-enabled device, suitable for use with an RFID system including an RFID reader configured to extract information from an RFID chip associated with the RFID-enabled device, includes a personal data protection system including a personal data protection device configured to prevent reading of the RFID chip associated with an RFID-enabled personal item.

Abstract: A hub-and-spoke radio frequency identification (“RFID”) inventory management system includes a distributed information-handling architecture together with consolidated access to system-wide information through cloud services. The system allows each supplier, hub, and point-of-use (“POU”) user interface to have consolidated access, visibility, analysis, and on-demand reporting of RFID data along with inventory management services implemented by one or more cloud services platforms. The cloud services can be provisioned on item-by-item, user-by-user, facility-by-facility bases in accordance with a hierarchical permission-based access system. The cloud services generally include, for example, a system of inventory management dashboards customizable to provide the specific inventory management information most pertinent for each user, supplier, hub, and POU.

Abstract: Scanners with wakeup systems are disclosed herein. An example scanner assembly includes a wakeup system having an infrared (IR) transmitter configured to project IR illumination through a window of the scanner and an IR receiver. The IR receiver has a second field-of-view (FOV) directed through the window that overlaps a first FOV of an imaging assembly of the scanner by at least 50% at the window and has a second central axis that is non-perpendicular to the window such that the second central axis is tilted downward from horizontal with the scanner assembly positioned in a vertical first configuration where the window is in a generally upright orientation. A controller of the scanner is configured to activate an illumination system when the IR receiver detects IR illumination reflected from an object in the second FOV of the IR receiver.

Abstract: Methods and apparatus for providing out-of-range indications are disclosed. An example imaging reader includes an image sensor and an optical assembly. The imaging reader may include a distance determining module configured to determine a distance to a target. The imaging reader may include an indication determining module configured to determine an out-of-range indication when the distance satisfies a first condition. An indicator may be included and configured to present the out-of-range indication. The image sensor may be configured to capture a representation of an image of the target when the distance satisfies a second condition. The imaging reader may include an indicia decoder configured to decode an indicia in the representation to determine an indicia payload and/or a communication interface to convey the indicia payload to a host system.

Abstract: A method for locating an optical code, on the basis of a finder pattern of the optical code, in an image having a plurality of pixels, the method comprising the steps of determining at least one candidate position for the finder pattern on the basis of edge transitions along at least one line through the image; determining a final position of the finder pattern in a vicinity of the candidate position; and verifying the final position, i.e. verifying that the image comprises the finder pattern in the final position, using a known property of the finder pattern.

Abstract: An image processing apparatus that performs image processing of document data including link destination information converted to a code data image. The document data is displayed, and in a case where the code data image is detected from the document data, link destination information is extracted from the detected code data image. Whether or not to set each of the document data and information indicated by the link destination information as an object to be printed is selected by a user. When a print instruction is received from a user, the document data is printed in a case where the document data has been selected as the object to be printed, and the information indicated by the link destination information is printed in a case where the information indicated by the link destination information has been selected as the object to be printed.

Abstract: The information processing apparatus receives a print job from an external apparatus and generates, from print data included in the print job, image data for printing and image area attribute information related to content for each area included in an image to be printed. In addition, for an area in which the image area attribute information indicates a text string attribute, the information processing apparatus extracts, from the print data, direction information related to an orientation of a text string and transmits, to the printing apparatus, the image area attribute information and the direction information, together with the image data for printing. The inspection apparatus inspects a printed product according to the image data for printing, by comparing a read image of the printed product, and a reference image, which is received image data for printing, according to the image area attribute information and the direction information.

Abstract: A method of controlling an inkjet printer when printing on a substrate that is to be shrink wrapped on to an object (10), by loading an image file on to a raster image processor; undertaking raster image processing on the loaded image file to generate raster image data for controlling discharge of ink droplets on to the substrate; receiving an indication of a shape (19) of the object (10); and manipulating the generated raster image data in response to the indication of the shape (19) of the object (10) to alter the distribution and/or size of droplets applied to the substrate to take into account anticipated changes (14) in a dimension (11, 12, 13) of the substrate due to shrinkage into contact with the object (10). Also a printer for carrying out the method.

Abstract: A quick response tag is provided. The tag includes a body having a front side and a back side, the front side having a laser engraved QR code and the back side having a laser engraved QR code. The tag further includes a first leg and a second leg extending from the top of the body.

Abstract: A device for the automatic fitting of vehicle registration plates with data carriers. A plurality of work stations interlinked by at least one conveyor are provided for this purpose. The work stations are equipped with handling devices and associated imaging devices. As a result, a respective data carrier can be automatically gripped and placed in its precise position in the opening and prefixed there. The data carriers are then each cast automatically in the opening for the permanent fixation of the data carrier in the opening of the registration plate.

Abstract: Embodiments of the present disclosure relate to methods, devices and computer readable media for adaptive configuration of multistatic harmonic tag backscatter. A network device transmits, to an illuminator for a passive tag, a request for transmitting an activation signal to a passive tag at a primary frequency and a first transmission power. The network device receives, from the illuminator, information about a harmonic frequency of a harmonic of the activation signal back-scattered from the passive tag, a received level of the harmonic and a distance between the illuminator and the passive tag. The network device selects at least one reader for the passive tag. The network device configures the illuminator to transmit the activation signal to the passive tag at the primary frequency. The network device configures the at least one reader to receive the harmonic of the activation signal at the harmonic frequency.

Abstract: An example disclosed method for authenticating a radio frequency identification (“RFID”) tag includes receiving a first signal including a first transponder identifier associated with the RFID tag; receiving a second signal including a second transponder identifier, wherein the second transponder identifier is associated with a different transponder than the first transponder identifier; and determining, with circuitry, whether the second transponder identifier is associated with the RFID tag.

Abstract: A chip arrangement including a chip module which includes a chip, a contact-based interface in accordance with ISO 7816 which is electrically conductively connected to the chip, and an antenna structure which is electrically conductively connected to the chip and provides a contactless interface, and a carrier which comprises a chip module receptacle and a booster antenna structure which, when the chip module is arranged in the chip module receptacle of the carrier, inductively couples to the antenna structure of the chip module, wherein the chip module is arranged releasably in the chip module receptacle.

Abstract: A radio-frequency identification (RFID) tag, wherein an operational characteristic of the tag is susceptible to influence by a material comprising an object to which it is attached, comprising: a substrate comprising an attachment region and a flap region, the attachment region for coupling the RFID tag to a surface of an object; and, an RFID inlay formed on the substrate, comprising a loop antenna and a dipole antenna, the loop antenna and the dipole antenna each having first and second portions within the attachment and flap regions, respectively, wherein a relative portion of the loop antenna within the attachment region has a positive influence on the operational characteristic when attached to an object and a relative portion of the dipole antenna within the attachment region has a negative influence on the operational characteristic, whereby the net influence on the operational characteristic by the object can be minimized.

Abstract: A system includes a metal detector configured to provide an input signal responsive to being proximate an object; and a processing device configured to: receive the input signal from the metal detector; determine a plurality of features from the input signal; provide the plurality of features as input to a trained machine learning model (MLM); receive output from the trained MLM; and responsive to detection, based on the output, that the object comprises metal, cause output of a notification.

Abstract: One example method includes registering, by a customer, with a service provider, receiving, by the customer from the service provider, a global machine learning model, running, by the customer, the global machine learning model as a local machine learning model, collecting, by the customer, unlabeled data generated by edge devices operating in a customer domain, checking, by the customer, to determine if the customer domain has changed, and when it is determined that the customer domain has changed, performing, by the customer, a model adaptation process on the local machine learning model, and transmitting to the service provider, by the customer, gradients that comprise customer implemented changes to the local machine learning model.

Abstract: A dynamic modular neural network (DMNN) for NOx emission prediction in MSWI process is provided. First, the input variables are smoothed and normalized. Then, a feature extraction method based on principal component analysis (PCA) was designed to realize the dynamic division of complex conditions, and the prediction task to be processed was decomposed into sub-tasks under different conditions. In addition, aiming each sub-tasks, a long short-term memory (LSTM)-based sub-network is constructed to achieve accurate prediction of NOx emissions under various working conditions. Finally, a cooperative strategy is used to integrate the output of the sub-networks, further improving the accuracy of prediction model. Finally, merits of the proposed DMNN are confirmed on a benchmark and real industrial data of a municipal solid waste incineration (MSWI) process. The problem that the NOx emission of MSWI process is difficult to be accurately predicted due to the sensor limitation is effectively solved.

Abstract: A first distribution estimating device determines a first probability distribution of quantized values in a predetermined value range corresponding to an input value, by using a first machine learning model. A first sampling device samples the quantized values and determines a first sample value, using the first probability distribution. A second distribution estimating device determines a second probability distribution corresponding to the first sample value, by using a second machine learning model. A second sampling device samples the quantized values in the value range and determines a second sample value, using the second probability distribution. It can be implemented in the form of any of an information processing system, an encoding device, a decoding device, a model learning device, an information processing method, an encoding method, a decoding method, a model learning method, and a program storage medium.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a prediction of an audio signal. One of the methods includes receiving a request to generate an audio signal; obtaining a semantic representation of the audio signal; generating, using one or more generative neural networks and conditioned on at least the semantic representation, an acoustic representation of the audio signal; and processing at least the acoustic representation using a decoder neural network to generate the prediction of the audio signal.

Abstract: Disclosed is a massive data-driven method for automatically locating a mine microseismic source, including: constructing a microseismic wave calibration data set by using a large-scale seismic data set containing seismic signals and non-seismic signals; constructing a pre-training calibration model based on a full convolution neural network through deep learning of a seismic wave calibration data set; using microseismic data of mine sites for transfer learning of an initial arrival time calibration model to construct an arrival time automatic calibration model suitable for mine microseismic signals; and automatically as well as accurately locating mine microseismic events based on an isokinetic homogeneous isotropic velocity model by using an optimization algorithm to deduce arrival time errors and through repeated iteration and fine-tuning.

Abstract: Methods and apparatuses are provided for entropy encoding and decoding of a latent tensor, which includes separating the latent tensor into patches and obtaining a probability model for the entropy encoding of a current element of the latent tensor by processing a set of elements from different patches by one or more layers of a neural network. The processing of the set of elements by applying a convolution kernel enables sharing of information between the separated patches.

Abstract: A method may be provided for selecting embedding dimension, which can include receiving a trained machine learning (ML) model and a graph neural network (GNN) and extracting, from the received ML model, a count of a number of neurons in a penultimate layer and node embeddings for each input graph node in GNN neurons in the penultimate layer. An importance threshold input for filtering the node embeddings can be received, and a tree-based model may be used to return feature importance values. The extracted node embeddings may be input into the tree-based model and an importance metric of each of the node embedding dimensions may be determined from the penultimate layer neurons. The penultimate layer neuron count of the ML model may be restricted to correspond to a number of the highest importance node embedding dimensions and the ML model may be trained using the restricted penultimate layer.

Abstract: Described are a system, method, and computer program product for dynamic node classification in temporal-based machine learning classification models. The method includes receiving graph data of a discrete time dynamic graph including graph snapshots, and node classifications associated with all nodes in the discrete time dynamic graph. The method includes converting the discrete time dynamic graph to a time-augmented spatio-temporal graph and generating an adjacency matrix based on a temporal walk of the time-augmented spatio-temporal graph. The method includes generating an adaptive information transition matrix based on the adjacency matrix and determining feature vectors based on the nodes and the node attribute matrix of each graph snapshot.

Abstract: One embodiment of an accelerator includes a computing unit; a first memory bank for storing input activations and a second memory bank for storing parameters used in performing computations, the second memory bank configured to store a sufficient amount of the neural network parameters on the computing unit to allow for latency below a specified level with throughput above a specified level. The computing unit includes at least one cell comprising at least one multiply accumulate (“MAC”) operator that receives parameters from the second memory bank and performs computations. The computing unit further includes a first traversal unit that provides a control signal to the first memory bank to cause an input activation to be provided to a data bus accessible by the MAC operator. The computing unit performs computations associated with at least one element of a data array, the one or more computations performed by the MAC operator.

Abstract: A system may comprise a neural processing unit (NPU) including a plurality of processing elements (PEs) capable of performing computations for at least one artificial neural network (ANN) model; and a switching circuit. The switching circuit may be configured to select one clock signal among a plurality of clock signals having different frequencies, and supply the selected clock signal to the NPU. The one clock signal may be selected based on a utilization rate of the plurality of PEs for a particular layer among a plurality of layers of the at least one ANN model.

Abstract: An artificial neuron network and corresponding neuron units are described and corresponding neuron units. The neuron network comprises a plurality of two or more layers of artificial neuron units. The layers of artificial neuron units are configured for communicating between them via an arrangement of two or more optical waveguide (optical fibers). The arrangement of two or more optical waveguides are configured with predetermined coupling between the two or more waveguides, thereby providing cross communication between neuron units of said two or more layers.

Abstract: An optical computing device includes a light diffraction element group including light diffraction elements each having an optical computing function, and a light emitter that generates signal light inputted into the light diffraction element group and indicative of images formed by different optical systems.

Abstract: The present invention discloses a two-dimensional photonic convolutional acceleration system and device for convolutional neural network, comprising: a multi-wavelength light source, a signal source to be convolved, a modulator, a dispersion module, a 1×M power divider, an optical fiber delay array, a microring weighting array chip, a convolutional kernel matrix control unit, a trans-impedance amplifier array, and an acquisition and processing unit. The present invention realizes two-dimensional convolutional acceleration based on wavelength-time interleaving technology, a single modulator can realize the optical domain loading of the signal, and the convolutional operation speed is only limited to the speed of the modulator.

Abstract: An optoelectronic computing system includes a first semiconductor die having a photonic integrated circuit (PIC) and a second semiconductor die having an electronic integrated circuit (EIC). The PIC includes optical waveguides, in which input values are encoded on respective optical signals carried by the optical waveguides. The PIC includes an optical copying distribution network having optical splitters. The PIC includes an array of optoelectronic circuitry sections, each receiving an optical wave from one of the output ports of the optical copying distribution network, and each optoelectronic circuitry section includes: at least one photodetector detecting at least one optical wave from the optoelectronic operation. The EIC includes electrical input ports receiving respective electrical values.

Abstract: A vision transformer (ViT) is a deep learning model that performs one or more vision processing tasks. ViTs may be modified to include a global task that clusters images with the same concept together to produce semantically consistent relational representations, as well as a local task that guides the ViT to discover object-centric semantic correspondence across images. A database of concepts and associated features may be created and used to train the global and local tasks, which may then enable the ViT to perform visual relational reasoning faster, without supervision, and outside of a synthetic domain.

Abstract: A computer implemented method of a machine learning algorithm modelling a target function mapping inputs in an input domain to outputs in an output range, the machine learning algorithm including an array of processing nodes arranged in a network of layers of nodes including an input layer for receiving an input value, an output layer for providing an output value, and one or more intermediate layers between the input and output layers, each node in the processing set being outside the input layer receiving input from at least some adjacent nodes logically closer to the input layer via weighted connections between nodes, and each node being outside the output layer generating output to at least some adjacent nodes logically closer to the output layer via weighted connections between nodes, wherein each node includes: an adjustable weight for application to each input to the node, the adjustment weight being responsive to a threshold function applied to a value of the node input; a combination function for com

Abstract: A method for energy-efficient classification receiving, via a first circuit, an input data stream from one or more sensors. The first circuit detects, while a second circuit is in a dormant state, if a state change has occurred between a first input of the input data stream and a second input of the input data stream. The second input is a next succeeding input of the input data stream. The first circuit triggers the second circuit to perform a classification of the input data stream in response to detecting the state change.

Abstract: There is provided an apparatus which can include a first module and a second module coupled to the first module. The first module can be configured to receive at least one input signal and/or generate at least one input signal. The input signal can be associated with at least one operating parameter and/or at least one target variable, associable with a structure (e.g., a pipeline). The second module can be configured to process the input signal by manner of data cleaning, data wrangling and/or data merging, to produce at least one output signal communicable for further processing (e.g., Machine-Learning based processing).

Abstract: According to a second aspect, it is provided a method for enabling collaborative machine learning. The method is performed by an agent device. The method includes the steps of: obtaining local input data; generating read interface parameters based on the local input data using a controller neural net; generating write interface parameters; transmitting a central reading request to the central device; receiving a central reading from the central device; updating the controller neural net of the agent device based on the central reading; and providing a predictor output of local input data based on the controller neural net and a second model of the agent device, the second model having as an input an output of the controller neural net, wherein the predictor output is obtained from the second model.

Abstract: A neural network model training method, a data processing method, and an apparatus are disclosed. The neural network model training method includes: training a neural network model based on training data, where an activation function of the neural network model includes at least one piecewise function, and the piecewise function includes a plurality of trainable parameters; and updating the plurality of trainable parameters of the at least one piecewise function in a training process. According to the method, the activation function suitable for the neural network model can be obtained. This can improve performance of the neural network model.

Abstract: A method includes: receiving data identifying, for each of one or more objects, a respective target location to which a robotic agent interacting with a real-world environment should move the object; causing the robotic agent to move the one or more objects to the one or more target locations by repeatedly performing the following: receiving a current image of a current state of the real-world environment; determining, from the current image, a next sequence of actions to be performed by the robotic agent using a next image prediction neural network that predicts future images based on a current action and an action to be performed by the robotic agent; and directing the robotic agent to perform the next sequence of actions.

Abstract: A computer-implemented method for learning disentangled representations for T-cell receptors to improve immunotherapy is provided. The method includes optionally introducing a minimal number of mutations to a T-cell receptor (TCR) sequence to enable the TCR sequence to bind to a peptide, using a disentangled Wasserstein autoencoder to separate an embedding space of the TCR sequence into functional embeddings and structural embeddings, feeding the functional embeddings and the structural embeddings to a long short-term memory (LSTM) or transformer decoder, using an auxiliary classifier to predict a probability of a positive binding label from the functional embeddings and the peptide, and generating new TCR sequences with enhanced binding affinity for immunotherapy to target a particular virus or tumor.

Abstract: Methods and systems for training a language model include retrieving a knowledge sentence, related to an input sentence, from a knowledge base. The input sentence, the knowledge sentence, and a prompt are encoded into an intermediate representation. The intermediate representation is decoded to generate a named entity from the input sentence that is of a type specified by the prompt. A language model is fine-tuned based on the named entity.

Abstract: A self-tuning model compression methodology for reconfiguring a Deep Neural Network (DNN) includes: receiving a pre-trained DNN model and a data set; performing an inter-layer sparsity analysis to generate a first sparsity result; and performing an intra-layer sparsity analysis to generate a second sparsity result, including: defining a plurality of sparsity metrics for the network; performing forward and backward passes to collect data corresponding to the sparsity metrics; using the collected data to calculate values for the defined sparsity metrics; and visualizing the calculated values using at least a histogram.

Abstract: In training a deep neural network using reduced precision, gradient computation operates on larger values without affecting the rest of the training procedure. One technique trains the deep neural network to develop loss, scales the loss, computes gradients at a reduced precision, and reduces the magnitude of the computed gradients to compensate for scaling of the loss. In one example non-limiting arrangement, the training forward pass scales a loss value by some factor S and the weight update reduces the weight gradient contribution by 1/S. Several techniques can be used for selecting scaling factor S and adjusting the weight update.

Abstract: The system receives a plurality of medical images and integrates Self-Supervised machine Learning (SSL) instructions for performing a discriminative learning operation, a restorative learning operation, and an adversarial learning operation into a model for processing the received plurality of medical images. The model is configured with each of a discriminative encoder, a restorative decoder, and an adversarial encoder. Each of the discriminative encoder and the restorative decoder are configured to be skip connected, forming an encoder-decoder.

Abstract: Systems and methods for unit test generation using reinforcement learning augmented transformer architectures are disclosed. A method may include: receiving raw data for source code from a database; identifying a function for which a unit test will be generated and an existing unit test for that function; receiving the function and the existing unit test; generating a generated unit test for the function using the function for the unit test and the existing unit test using a deep learning model; applying a loss function to the generated unit test, wherein the loss function is based on a comparison between the generated unit test and the existing unit test and results of the application of the loss function are fed back to the transformer computer program; simulating the generated unit test using a simulator; generating scalar feedback; and refining the generated unit test using the scalar feedback.

Abstract: A method for generating adversarial examples for a Graph Neural Network (GNN) model. The method includes: determining vulnerable features of target nodes in a graph based on querying the GNN model, wherein the graph comprising nodes including the target nodes and edges, each of the edges connecting two of the nodes; grouping the target nodes into a plurality of clusters according to the vulnerable features of the target nodes; and obtaining the adversarial examples based on the plurality of clusters.

Abstract: A method for training a generative adversarial network. The method includes: iteratively training the generative adversarial network based on the training data, the training of the generative adversarial network including an alternating training of the generator and the discriminator based on the training data, the training of the generator including a training the generator based on the training data and results of realism assessments performed by the discriminator, and the training of the generative adversarial network in each iteration step including a generation of corresponding data by the generator, a performance of a realism assessment of the corresponding data by the discriminator, and a performance of an additional realism assessment of at least one specific feature derived from the corresponding data by the discriminator, and the performance of the additional realism assessment of at least one specific feature derived from the corresponding data including an application of a deterministic function.

Abstract: In some embodiments, a method includes sending, from a first set of computing devices, a distributed instance of a machine learning model to a client computing device, where the client computing device is caused to provide a set of outputs related to the noise data, and where the set of outputs is an output of the distributed instance derived from inputting the noise data into the distributed instance. The method further includes receiving the set of outputs from the client computing device and configuring another instance of the machine learning model based on the noise data and the set of outputs related to the noise data.