Abstract: A system, method and computer program product for interfacing a decision engine and a marketing engine in order to provide vendor-related data in response to decision-related data is disclosed. In at least one embodiment, the system and method may include providing a decision engine on a user-accessible network; interfacing a marketing engine with the decision engine on the network; receiving a plurality of user inputs with the decision engine; processing decision-related data with the decision engine in accordance with the plurality of user inputs; sharing the decision-related data with the marketing engine; processing the decision-related data with the marketing engine; and transmitting vendor-related data via the network.

Abstract: Methods for generating data models using a generative adversarial network can begin by receiving a data model generation request by a model optimizer from an interface. The model optimizer can provision computing resources with a data model. As a further step, a synthetic dataset for training the data model can be generated using a generative network of a generative adversarial network, the generative network trained to generate output data differing at least a predetermined amount from a reference dataset according to a similarity metric. The computing resources can train the data model using the synthetic dataset. The model optimizer can evaluate performance criteria of the data model and, based on the evaluation of the performance criteria of the data model, store the data model and metadata of the data model in a model storage. The data model can then be used to process production data.

Abstract: A system and computer implemented method for learning rules from a data base including entities and relations between the entities, wherein an entity is either a constant or a numerical value, and a relation between a constant and a numerical value is a numerical relation and a relation between two constants is a non-numerical relation. The method includes: deriving aggregate values from said numerical and/or non-numerical relations; deriving non-numerical relations from said aggregate values; adding said derived non-numerical relations to the data base; constructing differentiable operators, wherein a differentiable operator refers to a non-numerical or a derived non-numerical relation of the data base, and extracting rules from said differentiable operators.

Abstract: A system for event prediction using schema networks includes a first antecedent entity state that represents a first entity at a first time; a first consequent entity state that represents the first entity at a second time; a second antecedent entity state that represents a second entity at the first time; and a first schema factor that couples the first and second antecedent entity states to the first consequent entity state; wherein the first schema factor is configured to predict the first consequent entity state from the first and second antecedent entity states.

Abstract: A method includes receiving input that identifies one or more data sources and determining, based on the input, a machine learning problem type of a plurality of machine learning problem types supported by an automated model building (AMB) engine. The method also includes generating an input data set of the AMB engine based on application of one or more rules to the one or more data sources. The method further includes, based on the input data set and the machine learning problem type, initiating execution of the AMB engine to generate a neural network configured to model at least a portion of the input data set.

Abstract: Methods, systems, and devices for an artificial neural network are described. In one example, an artificial neuron in an artificial neural network may include a resistor coupled with an input line and configured to indicate a synaptic weight and a fuse coupled with the resistor. The artificial neuron may also include a selection component coupled with the fuse and configured to activate the fuse for programming the resistor, and a second selection component coupled with the resistor and an output line, the second selection component configured to select the resistor for a read operation.

Abstract: An Artificial Intelligence (AI) based automatic damage detection and estimation system receives images of a damaged object. The images are converted into monochrome versions if needed and analyzed by an ensemble machine learning (ML) cause prediction model that includes a plurality of sub-models that are each trained to identify a cause of damage to a corresponding portion for the damaged object from a plurality of causes. In addition, an explanation for the selection of the cause from the plurality of causes is also provided. The explanation includes image portions and pixels of images that enabled the cause prediction model to select the cause of damage. An ML parts identification model is also employed to identify and labels parts of the damaged object which are repairable and parts that are damaged and need replacement. The cost estimation for the repair and restoration of the damaged object can also be generated.

Abstract: A neural network accelerating method and device includes: reading a total video memory size available for a GPU to execute computing of a neural network, setting a size of a configurable level, and determining a finest granularity of a factor used for splitting a workspace; generating an optimal acceleration solution architecture for determining an optimal batchsize and an optimal network layer configuration that enable fastest convolution execution; generating a state transition equation for a multiple knapsack problem by taking a convolution operation efficiency boundary condition in the optimal acceleration solution architecture as a fitness function; iterating the state transition equation by using a genetic algorithm taking a forward and back convolution function as evaluation bases until a convergent batchsize and network layer configuration are obtained, and accelerating the neural network by taking the convergent batchsize and the network layer configuration as the optimal batchsize and the optimal ne

Abstract: Systems and methods for generating a chatbot are disclosed. Source data is identified. A first chunk of the source data is also identified. A first machine learning model is executed for automatically generating a first candidate question associated with the first chunk. A determination is made as to whether the first candidate question satisfies a criterion. The first candidate question is output as training data for training the chatbot in response to the determination.

Abstract: An example a method of optimizing a neural network having a plurality of layers includes: obtaining an architecture constraint for circuitry of an inference platform that implements the neural network; training the neural network on a training platform to generate network parameters and feature maps for the plurality of layers; and constraining the network parameters, the feature maps, or both based on the architecture constraint.

Abstract: A cashierless tracking system uses a biometric sensor disposed at the entry of a store or the entry of a shelf or an entry to a section of a store is configured to capture biometric feature aspects of a user. Cashierless shopping is enabled without requiring a user to supply mobile phone or device to identify themselves. Instead, processing and classification of biometric features occur via a neural network to identify at least one label representing classified features of the user, the label being used to identify a profile for the user. A plurality of sensors in the store produces data to identify a take of an item by a single user or by a group of users tied to a single account. Included tracking embodiments involve overlapping cameras, skeletal tracking, microphone input, feature extraction and/or feature engineering. The take of the item is chargeable to an electronic shopping cart of the user.

Abstract: A quantum computer includes an efficient and exact quantum circuit for performing quantum state compression.

Abstract: A processing node in a temporal memory system includes a spatial pooler and a sequence processor. The spatial pooler generates a spatial pooler signal representing similarity between received spatial patterns in an input signal and stored co-occurrence patterns. The spatial pooler signal is represented by a combination of elements that are active or inactive. Each co-occurrence pattern is mapped to different subsets of elements of an input signal. The spatial pooler signal is fed to a sequence processor receiving and processed to learn, recognize and predict temporal sequences in the input signal. The sequence processor includes one or more columns, each column including one or more cells. A subset of columns may be selected by the spatial pooler signal, causing one or more cells in these columns to activate.

Abstract: An artificial intelligence (AI) system capable of simulating functions of a human brain, such as recognition and judgment, by using the machine learning algorithm such as deep learning, and an application thereof are provided. A method of learning multi-modal data according to the AI system and an application thereof includes: obtaining first context information representing a characteristic of a first signal and second context information representing a characteristic of a second signal by using a first learning network model; obtaining hidden layer information based on the first context information and the second context information by using a second learning network model; obtaining a correlation value representing a relation degree between the hidden layer information by using the second learning network model; and learning the hidden layer information in which the correlation value is derived as a maximum value.

Abstract: Systems and methods for presenting inference models based on interrelationships among inference models are provided. For example, information related to a group of at least three inference models may be obtained. Further, in some examples, a plurality of interrelationship records may be obtained, wherein each interrelationship record may correspond to one subgroup of the group of at least three inference models, and each subgroup may comprise at least two inference models. Further, in some examples, the plurality of interrelationship records may be used to determine information related to a first inference model of the group of at least three inference models. Further, in some examples, the determined information may be used to present the first inference model to a user.

Abstract: Methods and systems related to tracking activity in a store in association with a cashier-less environment are provided. One example method includes identifying actions in a store. The method includes sampling a shopping environment using one or more sensors that include at least one camera capable of providing depth sensing to produce image data of a scene that shows a shopper in the store and tracking data related to one or more limbs of the shopper in connection to an item. The method includes receiving output of the sampling as feature inputs to one or more machine learning models and deriving one or more label inferences of a behavior state of the shopper in connection with a state of the item. At least one processing entity associated with the store detects the state of the item to change from one as item handled by said shopper to one as item queued for purchase.

Abstract: Described herein is a technology that facilitates the production of and the use of automated datagens for event-based systems. A datagen (i.e., data-generator or data generation system) is a component, module, or subsystem of computer systems that searches, monitors, and analyzes machine data. Existing datagens are not capable of detecting an anomaly in machine data. An anomaly is a variance in the input data stream that exceeds some acceptable amount of deviation from the norm (i.e., standard, expectation, etc.). An embodiment of datagen, in accordance with the technology described herein, detects anomalies in the input machine data.

Abstract: An exemplary system, method, and computer-accessible medium can include, for example, (a) receiving a dataset(s), (b) determining if a misclassification(s) is generated during a training of a model(s) on the dataset(s), (c) generating a synthetic dataset(s) based on the misclassification(s), and (d) determining if the misclassification(s) is generated during the training of the model(s) on the synthetic dataset(s). The dataset(s) can include a plurality of data types. The misclassification(s) can be determined by determining if one of the data types is misclassified. The dataset(s) can include an identification of each of the data types in the dataset(s).

Abstract: Because digital assistants tend to have different areas of expertise and/or different abilities to fulfill a given request, it is sometimes difficult for a user to know which digital assistant is best able to fulfill a request. Representative embodiments disclose mechanisms to increase federate digital assistants so that a user's request can be funneled to the digital assistant best able to fulfill the user's request. A meta-assistant gathers information on skills provided by a set of digital assistants. The meta-assistant also gathers completion data for requests for different digital assistants and user satisfaction information. A user submits a request to the meta-assistant. The meta-assistant extracts user intent from the request and redirects the user's request to the digital assistant best able to fulfill the request. Embodiments can utilize trained machine learning models or scored algorithmic approaches to select the digital assistant.

Abstract: Method and systems are provided for processing actions in a store. One example method includes capturing sensor output from two or more sensors in a shopping environment. One sensor includes a first camera to capture scene data where the scene includes movement of a shopper in the store performing interaction with an item in the store. Another sensor includes a second camera capturing at least part of the scene from a different perspective. The method includes processing, by a processing entity associated with the store, at least one of the camera's output to generate feature data. The feature data is processed by one or more machine learning models to produce engineered feature data. The engineered feature data includes data relating to tracking skeletal movement of shopper.