Abstract: This disclosure provides systems, methods, and apparatus for determining whether an incident radio-frequency (RF) signal is from a known transmission source based on a match between a signature of the incident RF signal and at least one stored signature. One or more antennas can generate a plurality of electrical signals corresponding to a portion of a pulse of the incident RF signal. At least one of amplitude or phase values of a first electrical signal and phase coherent second electrical signal can be determined in the frequency domain. The signature of the incident RF signal based on at least one of amplitude or phase values of the first and the second electrical signals can be determined. This signature can be compared with stored signatures to determine whether the incident RF signal is from a known transmission source.

Abstract: Systems and methods for lifelong schema matching are described. The systems and methods include receiving data comprising a plurality of information categories, classifying each information category according to a schema comprising a plurality of classes, wherein the classification is performed by a neural network classifier trained based on a lifelong learning technique using a plurality of exemplar training sets, wherein each of the exemplar training sets includes a plurality of examples corresponding to one of the classes, and wherein the examples are selected based on a metric indicating how well each of the examples represents the corresponding class, and adding the data to a database based on the classification, wherein the database is organized according to the schema.

Abstract: For reducing oscillations in a technical system plurality of different controller settings for the technical system is received. For a respective controller setting signal representing a time series of operational data of the technical system controlled by the respective controller setting is received, the signal is processed, whereby the processing includes a transformation into a frequency domain, and an entropy value of the processed signal is determined. Depending on the determined entropy values a controller setting from the plurality of controller settings is selected, and the selected controller setting is output for configuring the technical system.

Abstract: A method for operating a multi-agent system including multiple robots. Each robot cyclically carries out the following: starting from an instantaneous system state, ascertaining possible options, the options defining actions via which a transition from an instantaneous system state to a subsequent system state may be achieved; for each possible option, ascertaining action costs for carrying out an action indicated by the option; carrying out an auction, the action cost values ascertained for each option being taken into account by each of the other robots; and executing an action that corresponds to one of the options as a function of all cost values ascertained or received for the option in question, the action costs for an option taking into account an empirical parameter that is a function of costs for past actions, which have already been carried out and which are associated with the option, of the multiple robots.

Abstract: A method for selecting an AI solution for an automated robotic process including receiving at least one functional media including information indicative of brain activity by a human engaged in a task of interest, analyzing the functional media, identifying an activity level in at least one brain region, identifying a brain region parameter and an activity parameter; identifying an action parameter based in part on the brain region parameter or the activity parameter; and selecting a component of the AI solution in part on the brain region parameter, the activity parameter, or the action parameter.

Abstract: An information processing apparatus (2000) acquires input data (10) and generates, by use of a neural network (30), condition data (50) that indicate one or more conditions satisfied by the input data (10). The information processing apparatus (2000) determines prediction data (20) by use of a value determined based on correct answer data (42) associated with example data (40) that satisfy at least a part of conditions indicated by the condition data (50).

Abstract: The network comprises at least one network layer in which a plurality of electronic oscillators, interconnected via programmable coupling elements storing respective network weights, generate oscillatory signals at time delays dependent on the input signal to propagate the input signal from an input to an output of that layer. The network is adapted to provide a network output signal dependent substantially linearly on phase of oscillatory signals in the last layer of the network. The method includes calculating a network error dependent on the output signal and a desired output for the training sample, and calculating updates for respective network weights by backpropagation of the error such that weight-updates for a network layer are dependent on a vector of time delays at the input to that layer and the calculated error at the output of that layer.

Abstract: Examples of biomimetic codecs and biomimetic coding techniques are described herein. Morphologically-adaptive coding networks can be developed in accordance with energy dissipation driven “heat” generated by application of training data. The morphologically-adaptive coding networks may be representative of common features expected in an input signal or data stream. Decoding may proceed using the morphologically-adaptive coding network. Morphologically-adaptive coding networks may be used as a cortex that can be shared for boosting multimedia data compression rates and/or increasing the encode-decode fidelity of information content while the features remain queryable in encoded form. Examples of the biomimetic codecs and biomimetic coding techniques provide a broad-based technology platform that can be used in context-IDed multimedia storage, pattern recognition, and high-performance computing/big data management, the hallmarks of web- and cloud-based systems.

Abstract: A method of providing intelligent software is provided. According to the present disclosure, it is possible to request an optimal AI model on the basis of a pre-trained AI model and meta information of the AI model, and it is possible to easily provide an AI model optimized for an intelligence device by responding to the request by creating a plurality of AI differentiation models from the AI model in accordance with a plurality of differentiation levels.

Abstract: In a case of achievement of a neural network circuit using a plurality of nonvolatile memory cells, a technique capable of accurately reading information recorded in the plurality of nonvolatile memory cells is provided. A semiconductor device includes: a plurality of nonvolatile memory cells; a plurality of reference-current cells; and a sense amplifier comparing an electric current flowing in each of the plurality of nonvolatile memory cells and an electric current flowing in each of the plurality of reference-current cells. In this case, each cross-sectional structure of the plurality of reference-current cells is the same as each cross-sectional structure of the plurality of nonvolatile memory cells. The writing operation or the erasing operation is also performed to each of the plurality of reference-current memory cells when the writing operation or the erasing operation is performed to each of the plurality of nonvolatile memory cells.

Abstract: Methods, systems, and devices for wireless communications are described. In some examples, a wireless communications system may support machine learning and may configure a user equipment (UE) for machine learning. The UE may transmit, to a base station, a request message that includes an indication of a machine learning model or a neural network function based at least in part on a trigger event. In response to the request message, the base station may transmit a machine learning model, a set of parameters corresponding to the machine learning model, or a configuration corresponding to a neural network function and may transmit an activation message to the UE to implement the machine learning model and the neural network function.

Abstract: A simulation test is run on a first machine learning model trained using first training data historically collected over a time period. The first training data includes a set of training inputs and a set of target outputs. In response to a determination that a result of the simulation test run on the first machine learning model satisfies one or more criteria, a size of the set of target outputs of the first training data is determined. Second training data for training a second machine learning model is obtained. A size of a set of target outputs of the second training data meets or exceeds the size of the target outputs of the first training data. The second machine learning model is trained using the second training data.

Abstract: Systems are provided for improving computer security systems that are based on user risk scores. These systems can be used to improve both the accuracy and usability of the user risk scores by applying multiple tiers of machine learning to different the user risk profile components used to generate the user risk scores and in such a manner as to dynamically generate and modify the corresponding user risk scores.

Abstract: A data source configured to provide a representation of an environment of one or more agents is identified. Using a data set obtained from the data source, a neural network-based reinforcement learning model with one or more attention layers is trained. Importance indicators generated by the attention layers are used to identify actions to be initiated by an agent. A trained version of the model is stored.

Abstract: A virtual lane estimation system includes a memory device, a sensor and a computer. The memory device is configured to store a road map that corresponds to a portion of a road ahead of a vehicle. The sensor is configured to observe a plurality of trajectories of a plurality of neighboring vehicles that traverse the portion of the road. The computer is configured to initialize a recursive self-organizing map as a plurality of points arranged as a two-dimensional grid aligned with the road map, train the points in the recursive self-organizing map in response to the trajectories, generate a directed graph that contains one or more virtual lanes through the road map in response to the points trained to the trajectories, and generate a control signal that controls navigation of the vehicle through the portion of the road in response to the virtual lanes in the directed graph.

Abstract: A sensor element with excellent characteristics is provided. An electronic device including a power storage system with excellent characteristics is provided. A vehicle including a power storage system with excellent characteristics is provided. A novel semiconductor device is provided. The power storage system includes a storage battery, a neural network, and a sensor element; the neural network includes an input layer, an output layer, and one or a plurality of middle layers provided between the input layer and the output layer; a value corresponding to a first signal output from the sensor element is supplied to the input layer; the first signal is an analog signal; the sensor element includes a region in contact with a surface of the storage battery; and the sensor element has a function of measuring one or both of strain and temperature.

Abstract: A network-based work assignment platform is provided. Employers and workers are registered on the platform. A registered employer posts a temporary job on the platform. The platform matches a registered worker to the temporary job. The platform facilitates, coordinates, and monitors performance of the temporary job by the registered worker and processes payment to the registered worker for performance of the temporary job on behalf of the registered employer.

Abstract: An information processing method, performed by a computer, includes: obtaining second situational information related to a situation of at least one of a vehicle or surroundings of the vehicle at a second time point subsequent to a first time point; determining recommended content related to vehicle monitoring recommended to a second monitoring agent by inputting the second situational information to a trained model obtained by machine learning in which first situational information and a first monitoring result which is a result of monitoring by a first monitoring agent based on the first situational information are used, the first situational information being related to a situation of at least one of the vehicle or the surroundings of the vehicle at the first time point; generating presentation information for vehicle monitoring based on the recommended content determined; and causing a presentation device to output the presentation information.

Abstract: A method, computer program product, and system perform computations using a processor. A first instruction including a first index vector operand and a second index vector operand is received and the first index vector operand is decoded to produce first coordinate sets for a first array, each first coordinate set including at least a first coordinate and a second coordinate of a position of a non-zero element in the first array. The second index vector operand is decoded to produce second coordinate sets for a second array, each second coordinate set including at least a third coordinate and a fourth coordinate of a position of a non-zero element in the second array. The first coordinate sets are summed with the second coordinate sets to produce output coordinate sets and the output coordinate sets are converted into a set of linear indices.

Abstract: Aspects of the disclosure provide for mechanisms for identification of fields in documents using neural networks. A method of the disclosure includes obtaining a layout of a document, the document having a plurality of fields, identifying the document, based on the layout, as belonging to a first type of documents of a plurality of identified types of documents, identifying a plurality of symbol sequences of the document, and processing, by a processing device, the plurality of symbol sequences of the document using a first neural network associated with the first type of documents to determine an association of a first field of the plurality of fields with a first symbol sequence of the plurality of symbol sequences of the document.

Abstract: A method of operating an apparatus using a control system that includes at least one neural network. The method includes receiving an input value captured by the apparatus, processing the input value using the at least one neural network of the control system implemented on first one or more solid-state chips, and obtaining an output from the at least one neural network resulting from processing the input value. The method may also include processing the output with another neural network implemented on solid-state chips to determine whether the output breaches a predetermined condition that is unchangeable after an initial installation onto the control system. The aforementioned another neural network is prevented from being retrained. The method may also include the step of using the output from the at least one neural network to control the apparatus unless the output breaches the predetermined condition. Similar corresponding apparatuses are described.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to map workloads. An example apparatus includes a constraint definer to define performance characteristic targets of the neural network, an action determiner to apply a first resource configuration to candidate resources corresponding to the neural network, a reward determiner to calculate a results metric based on (a) resource performance metrics and (b) the performance characteristic targets, and a layer map generator to generate a resource mapping file, the mapping file including respective resource assignments for respective corresponding layers of the neural network, the resource assignments selected based on the results metric.

Abstract: A method of sparse intent clustering is provided. The method comprises identifying features in a number of electronic user reports created by a user and contained in a database, wherein the features include a title and description. The features of each user report are encoded into a binary vector. The binary vector for each user report is fed into an autoencoder neural network that creates a N-dimensional vector representing the user report. The float vectors representing the user reports are projected into a N-dimensional space. The float vectors are clustered according to cosine similarities, wherein each vector cluster represents an intent of the user in creating the reports. The intent of each vector cluster is then labeled.

Abstract: An apparatus includes a storage control unit that divides, into two-dimensional blocks, a feature image of a layer and stores the respective blocks in any one of a predetermined number of memories, a unit that determines a pattern for reading blocks from the memories based on information relating to an operation on the feature image, and a unit that reads blocks from the memories in accordance with the pattern. The storage control unit assigns repeatedly, for the two-dimensional blocks, the memories in a predetermined order from a head row/column along a row/column. In a second or a subsequent row/column, a memory, which the assignment is started, is shifted by a constant number from a previous row/column in the predetermined order.

Abstract: Some embodiments include a special-purpose hardware accelerator that can perform specialized machine learning tasks during both training and inference stages. For example, this hardware accelerator uses a systolic array having a number of data processing units (“DPUs”) that are each connected to a small number of other DPUs in a local region. Data from the many nodes of a neural network is pulsed through these DPUs with associated tags that identify where such data was originated or processed, such that each DPU has knowledge of where incoming data originated and thus is able to compute the data as specified by the architecture of the neural network. These tags enable the systolic neural network engine to perform computations during backpropagation, such that the systolic neural network engine is able to support training.

Abstract: A method of quantitatively evaluating a cognitive status and its future change from a medical image of an individual's brain, the method comprising scanning the individual's brain with a scanning device so as to acquire at least one medical brain image; processing the medical brain image to obtain at least one feature of the image; using a pre-established prediction model to determine a condition of the cognitive status and predict its future change based on the at least one feature obtained.

Abstract: Provided herein is an integrated circuit including, in some embodiments, a hybrid neural network including a plurality of analog layers, a digital layer, and a plurality of data outputs. The plurality of analog layers is configured to include programmed weights of the neural network for decision making by the neural network. The digital layer, disposed between the plurality of analog layers and the plurality of data outputs, is configured for programming to compensate for weight drifts in the programmed weights of the neural network, thereby maintaining integrity of the decision making by the neural network. Also provided herein is a method including, in some embodiments, programming the weights of the plurality of analog layers; determining the integrity of the decision making by the neural network; and programming the digital layer of the neural network to compensate for the weight drifts in the programmed weights of the neural network.

Abstract: A system is typically configured for customizing interconnectivity of one or more layers associated with a neural network architecture, wherein the neural network architecture is associated with an application, customizing functional transformation of the one or more layers associated with the neural network architecture, wherein each of the one or more layers comprises a custom transformation function, and generating a custom neural network architecture based on customizing the interconnectivity and the functional transformation of the one or more layers.

Abstract: A geometry of a substrate surface is received at a neural network. The neural network is trained using one or more training sets. Each training set comprises a different type of substrate geometry and a collection of manufacturing process parameters. The substrate is configured to receive at least one liquid droplet. A shape of the at least one droplet after it has been deposited on the substrate is determined based on the received geometry. An output representing the determined shape of the at least one droplet is produced.

Abstract: In various examples, the present disclosure relates to using temporal filters for automated real-time classification. The technology described herein improves the performance of a multiclass classifier that may be used to classify a temporal sequence of input signals—such as input signals representative of video frames. A performance improvement may be achieved, at least in part, by applying a temporal filter to an output of the multiclass classifier. For example, the temporal filter may leverage classifications associated with preceding input signals to improve the final classification given to a subsequent signal. In some embodiments, the temporal filter may also use data from a confusion matrix to correct for the probable occurrence of certain types of classification errors. The temporal filter may be a linear filter, a nonlinear filter, an adaptive filter, and/or a statistical filter.

Abstract: A circuit for performing energy-efficient and high-throughput multiply-accumulate (MAC) arithmetic dot-product operations and convolution computations includes a two dimensional crossbar array comprising a plurality of row inputs and at least one column having a plurality of column circuits, wherein each column circuit is coupled to a respective row input. Each respective column circuit includes an excitatory memristor neuron circuit having an input coupled to a respective row input, a first synapse circuit coupled to an output of the excitatory memristor neuron circuit, the first synapse circuit having a first output, an inhibitory memristor neuron circuit having an input coupled to the respective row input, and a second synapse circuit coupled to an output of the inhibitory memristor neuron circuit, the second synapse circuit having a second output. An output memristor neuron circuit is coupled to the first output and second output of each column circuit and has an output.

Abstract: A robot controller that controls a robot by automatically obtaining a controller capable of suitably controlling a wide range of robots. An image is acquired from an image capturing apparatus that photographs an environment including the robot. The robot is driven based on an output result obtained by inputting the image to a neural network. The neural network is updated according to a reward generated in a case where a plurality of virtual images photographed while changing an environmental condition of a virtual environment generated by virtualizing the environment and a state of a virtual robot are input to the neural network, and a policy of the virtual robot, which is output from the neural network, satisfies a predetermined condition.

Abstract: Systems, methods and apparatuses of radar Electronic Control Units (ECUs) of autonomous vehicles. A radar ECU can include: a memory configured to store a radar image and an Artificial Neural Network (ANN); an inference engine configured to use the (ANN) to analyze the radar image and generate inference results; and a communication interface coupled to a computer system of a vehicle to implement an advanced driver assistance system to operate the controls according to the inference results and a sensor data stream generated by sensors configured on the vehicle.

Abstract: The present disclosure is directed to a novel system for performing online reconfiguration of a neural network. Once a neural network has been implemented into a production environment, the system may use underlying construction logic to perform an in-situ reconfiguration of neural network elements while the neural network is live. The system may accomplish the reconfiguration by modifying the architecture of the neural network and/or performing adversarial training and/or retraining. In this way, the system may provide a way increase the performance of the neural network over time along one or more performance parameters or metrics.

Abstract: A method of training a reinforcement machine learning computer system. The method comprises providing a machine-learning computer programming language including a pre-defined plurality of reinforcement machine learning criterion statements, and receiving a training specification authored in the machine-learning computer programming language. The training specification defines a plurality of training sub-goals with a corresponding plurality of the reinforcement machine learning criterion statements supported by the machine-learning computer programming language. The method further comprises computer translating the plurality of training sub-goals from the training specification into a shaped reward function configured to score a reinforcement machine learning model configuration with regard to the plurality of training sub-goals.

Abstract: A method for scalable multi-task learning with convex clustering includes: extracting features from a dataset of a plurality of tasks; generating a graph from the extracted features, nodes of the graph representing linear learning models, each of the linear learning models being for one of the tasks; constraining the graph using convex clustering to generate a convex cluster constrained graph; and obtaining a global solution by minimizing a graph variable loss function, the minimizing the graph variable loss function comprising: introducing auxiliary variables for each connection between nodes in the convex cluster constrained graph; iteratively performing the following operations until convergence: updating the linear learning models by solving a sparse linear system; and updating the auxiliary variables by solving an equation having the auxiliary variables each be proportional to a vector norm for their respective nodes.

Abstract: According to one aspect, cooperative multi-goal, multi-agent, multi-stage (CM3) reinforcement learning may include training a first agent using a first policy gradient and a first critic using a first loss function to learn goals in a single-agent environment using a Markov decision process, training a number of agents based on the first policy gradient and a second policy gradient and a second critic based on the first loss function and a second loss function to learn cooperation between the agents in a multi-agent environment using a Markov game to instantiate a second agent neural network, each of the agents instantiated with the first agent neural network in a pre-trained fashion, and generating a CM3 network policy based on the first agent neural network and the second agent neural network. The CM3 network policy may be implemented in a CM3 based autonomous vehicle to facilitate autonomous driving.

Abstract: A method, system, and computer program product for abnormal data detection. According to the method, a plurality of data points collected at different time points are classified into a plurality of groups. A plurality of groups of potential abnormal data points are determined from the plurality of groups. Correlations between a first group of the plurality of groups of potential abnormal data points with other groups of potential abnormal data points are determined. In response to the first group of the plurality of groups of potential abnormal data points being uncorrelated to a majority of the other groups of potential abnormal data points based on the correlations, data points in the first group are identified as abnormal data points.

Abstract: The embodiments herein provide a framework for and specific implementations of machine learning (ML) analysis of incident, online chat, knowledgebase, skills, and perhaps other types of databases. The ML techniques described herein may include various forms of semantic analysis of textual information in these databases, such as clustering, term frequency, word embedding, paragraph embedding, and potentially other techniques. Advantageously, use of ML in the specific ways described herein can provide insights into this textual information that otherwise would be impossible to determine in an accurate or concise fashion.

Abstract: A system includes a memory and a node. The memory stores first and second log string correlithm objects. The node receives first and second real-world numerical values, and identifies a first sub-string correlithm object from the first log string correlithm object that corresponds to the first real-world numerical value. The node aligns the first and second log string correlithm objects such that the first sub-string correlithm object aligns with a sub-string correlithm object from the second log string correlithm object representing the logarithmic value of one. The node identifies a second sub-string correlithm object from the second log string correlithm object that corresponds to the second real-world numerical value, and determines which sub-string correlithm object from the first log string correlithm object aligns with the second sub-string correlithm object from the second log string correlithm object. The node outputs the determined sub-string correlithm object.

Abstract: A convolutional neural network, and a processing method, a processing device, a processing system and a medium for the same.

Abstract: Some embodiments are associated with a system and method for deep learning unsupervised anomaly prediction in Internet of Things (IoT) sensor networks or manufacturing execution systems. The system and method use an unsupervised predictive GAN model with multi-layer perceptrons (MLP) as generator and discriminator.

Abstract: In an artificial neural network, integrality refers to the degree to which a neuron generates, for a given set of inputs, outputs that are near the border of the output range of a neuron. From each neural network of a pool of trained neural networks, a group of neurons with a higher integrality is selected to form a neural network tunnel (“tunnel”). The tunnel must include all input neurons and output neurons from the neural network, and some of the hidden neurons. Tunnels generated from each neural network in a pool are merged to form another neural network. The new network may then be trained.

Abstract: Systems and methods for adaptive data processing associated with complex dynamics are provided. The method may include applying the two or more predictive algorithms or rule-sets to an atomized model to generate applied data models. After receipt of inputs, the method may further include processing at least two propositions during a learning mode based upon detection of an absolute pattern within the applied data models; wherein propositions are action proposals associated with each predictive algorithm. At least two propositions may compete against each other through the use of an associated rating cell, which may be updated based upon the detected patterns. The method may further include processing propositions during an execution mode based upon detection of an absolute condition, wherein the rating cells are updated based upon these detected conditions. Further, these updated rating cells may be provided as feedback to update the atomized model.

Abstract: The present disclosure relates to systems and methods for floorplanning using machine learning techniques. Embodiments may include receiving an electronic design and analyzing the electronic design using a reinforcement learning agent. Embodiments may further include recommending a first action wherein the first action includes at least one of a place agent action, a via agent action, or a route agent action. Embodiments may also include updating the electronic design based upon, at least in part, the first action to generate an updated electronic design. Embodiments may further include analyzing the updated electronic design using the reinforcement learning agent and recommending a second action wherein the second action includes at least one of a place agent action, a via agent action, or a route agent action. Embodiments may also include updating the updated electronic design based upon the second action to generate a second updated electronic design.

Abstract: An N modular redundancy method, system, and computer program product include a computer-implemented N modular redundancy method for neural networks, the method including selectively replicating the neural network by employing one of checker neural networks and selective N modular redundancy (N-MR) applied only to critical computations.

Abstract: According to an embodiment, a neural network apparatus includes a plurality of neuron circuits, each including an integration circuit, a firing circuit, and a secondary battery. The integration circuit is configured to output an integral signal obtained by integrating input signals. The firing circuit is configured to generate, in accordance with the integral signal, a pulse signal to be transmitted to the neuron circuit provided at a subsequent layer. The secondary battery is configured to supply the firing circuit with drive electric power used for generating the pulse signal.

Abstract: A method and machine translation system for bi-directional translation of textual sequences between a first language and a second language are described. The machine translation system includes a first autoencoder configured to receive a vector representation of a first textual sequence in the first language and encode the vector representation of the first textual sequence into a first sentence embedding. The machine translation system also includes a sum-product network (SPN) configured to receive the first sentence embedding and generate a second sentence embedding by maximizing a first conditional probability of the second sentence embedding given the first sentence embedding and a second autoencoder receiving the second sentence embedding, the second autoencoder being trained to decode the second sentence embedding into a vector representation of a second textual sequence in the second language.

Abstract: An information processing method includes: reading a layer structure and parameters of layers from each of models of two neural networks; and determining a degree of matching between the models of the two neural networks, by comparing layers, of the respective models of the two neural networks, that are configured as a graph-like form in respective hidden layers, in order from an input layer using breadth first search or depth first search, based on similarities between respective layers.

Abstract: A search method for a neural network model structure, includes: generating an initial generation population of network model structure based on multi-objective optimization hyper parameters, as a current generation population of network model structure; performing selection and crossover on the current generation population of network model structure; generating a part of network model structure based on reinforcement learning mutation, and generating a remaining part of network model structure based on random mutation on the selected and crossed network model structure; generating a new population of network model structure based on the part of network model structure generated by reinforcement learning mutation and the remaining part of network model structure generated by random mutation; and searching a next generation population of network model structure based on the current generation population of network model structure and the new population of network model structure.