Abstract: Systems and methods improve the performance of a network that has converged such that the gradient of the network and all the partial derivatives are zero (or close to zero) by splitting the training data such that, on each subset of the split training data, some nodes or arcs (i.e., connections between a node and previous or subsequent layers of the network) have individual partial derivative values that are different from zero on the split subsets of the data, although their partial derivatives averaged over the whole set of training data is close to zero. The present system and method can create a new network by splitting the candidate nodes or arcs that diverge from zero and then trains the resulting network with each selected node trained on the corresponding cluster of the data. Because the direction of the gradient is different for each of the nodes or arcs that are split, the nodes and their arcs in the new network will train to be different. Therefore, the new network is not at a stationary point.

Abstract: A method and system for performing real time searches of large alphanumeric data sets including the following steps, combining a cognitive neuromorphic architecture with a neuron based encoding binary filter, wherein building the filter includes encoding input data as a concatenated binary representation, wherein the data becomes a binary value, connecting an axon to a neuron to create a synapse; wherein each binary value includes multiple axons and neurons, determining a weight to each synapse, applying the synaptic weight to the input data to determine an integrated value and determining if the integrated value is greater than or equal to a threshold value.

Abstract: A machine learning document processing system performs natural language processing (NLP) and machine learning to determine a subset of documents from a document dataset based on the structural features and semantic features. The system facilitates an interactive process, e.g., through a client application, to receive user input from a user to identify documents with a specific document feature category. The user input may be provided from a user as speech or text, and NLP is performed on the user input to determine user intent, the document features, and document feature category. Using the user intent and the additional document feature category, the system identifies subsets of the document dataset that matches the document feature category for display.

Abstract: A method and system for generating a probability value for an event. The system includes a source for generating a plurality of digital input signals, a processor connected to the source to receive the plurality of digital input signals from the source, and a display connected to the processor for displaying a final output. Preferably, the method further includes validating the probability value.

Abstract: Systems, methods, and computer-readable media are disclosed for determining recommended sizes of products using a machine learning model.

Abstract: A method for executing multi-directional reduction algorithms includes identifying a set of nodes, wherein a node includes at least one data element, creating a set of partitions including one or more data elements from at least two nodes, wherein the at least two nodes are arranged in a single direction with respect to the positioning of the set of nodes, executing a reduction algorithm on the data elements within the created set of partitions, creating an additional set of partitions including one or more data elements from at least two nodes, wherein the at least two nodes are arranged in a different direction with respect to the positioning of the set of nodes, executing a reduction algorithm on the data elements within the created additional set of partitions, and providing a set of reduced results corresponding to the at least one data element.

Abstract: An information processing apparatus includes a learning unit configured to learn a plurality of multi-layer neural networks configured to carry out a plurality of tasks, a generation unit configured to generate a shared layer candidate at a predetermined layer between or among the plurality of multi-layer neural networks, a first relearning unit configured to relearn the plurality of multi-layer neural networks in a structure using the shared layer candidate, and a determination unit configured to determine whether to share the shared layer candidate at the predetermined layer with respect to each of the plurality of tasks based on an evaluation of the relearning.

Abstract: The technology described herein allows an interactive program to leverage a knowledge graph to maximize the likelihood of successfully understanding the user's query and at the same time minimize the number of turns taken to understand the user. A goal of the technology described herein is to formulate response queries that have a probability of completing the user's requested task accurately while issuing the fewest number of response queries to the user before determining the intended task. In order to accomplish this, the technology combines a reinforced learning mechanism with a knowledge-graph simulation score to determine the optimal response query.

Abstract: In some embodiments, the present invention provides for a computer system which includes a content database storing initial content data and a vocabulary data set; a processor configured to applying a machine learning model to transform the initial content data into a N-dimensional vector space; self-training the machine learning model based on the vocabulary data set; applying a clustering technique to the N-dimensional vector space to generate a cluster model of clusters, where each cluster includes a plurality of word representations; associating each cluster with a cluster identifier; obtaining subsequent content data; associating each data element of the subsequent content data with each cluster to generate a content data cluster mapping model; continuously tracking, for each user, each respective cluster identifier of each respective cluster associated with each action performed by each user with each data element to continuously self-adapt each user-specific, time-specific dynamic cluster mapping model

Abstract: An apparatus comprises a memory and a processor coupled to the memory. The processor is configured to receive input from a cloud service data source, wherein the input comprises at least one data point, analyze the data point via a machine learning model to determine characteristics indicated by the data point, determine whether the characteristics indicated by the data point meet an alert threshold that indicates a problem in a network, generate an alert ticket when the characteristics indicated by the data point meet the alert threshold, wherein the alert ticket indicates the problem in the network, communicate with a user based on contents of the alert ticket, receive feedback from the user relating to the alert ticket, and train the machine learning model according to the feedback received from the user.

Abstract: Systems, methods, devices, and other techniques for planning a trajectory of a vehicle. A computing system can implement a trajectory planning neural network configured to, at each time step of multiple time steps: obtain a first neural network input and a second neural network input. The first neural network input can characterize a set of waypoints indicated by the waypoint data, and the second neural network input can characterize (a) environmental data that represents a current state of an environment of the vehicle and (b) navigation data that represents a planned navigation route for the vehicle. The trajectory planning neural network may process the first neural network input and the second neural network input to generate a set of output scores, where each output score in the set of output scores corresponds to a different location of a set of possible locations in a vicinity of the vehicle.

Abstract: Security systems and methods for detecting intrusion events include one or more sensors configured to monitor an environment. A pruned convolutional neural network (CNN) is configured process information from the one or more sensors to classify events in the monitored environment. CNN filters having the smallest summed weights have been pruned from the pruned CNN. An alert module is configured to detect an intrusion event in the monitored environment based on event classifications. A control module is configured to perform a security action based on the detection of an intrusion event.

Abstract: Devices, methods and articles advantageously allow communications between qubits to provide an architecture for universal adiabatic quantum computation. The architecture includes a first coupled basis A1B1 and a second coupled basis A2B2 that does not commute with the first basis A1B1.

Abstract: A neural network accelerator reads encoded weights from memory. All 1 bits in a weight except the first three are discarded. The first three leading 1 bits in the weight are encoded as three bit-shift values to form the encoded weight. The three bit-shift values are applied to a bit shifter to shift a node input to obtain three shifted inputs that are accumulated to generate the node output. Node complexity is reduced since only 3 shifts are performed rather than up to 15 shifts for a 16-bit weight. The bit shifter and accumulator for a node can be implemented by Look-Up Tables (LUTs) without requiring a Multiply-Accumulate (MAC) cell in a Field-Programmable Gate Array (FPGA). Quantization bias is reduced using a histogram analyzer that determines a weighted average for each interval between quantized weights. The third bit-shift value is incremented for weights in the interval above the weighted average.

Abstract: Disclosed are systems and methods for improving interactions with and between computers in content generating, searching, hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The systems interact to identify and retrieve data within or across platforms, which can be used to improve the quality of data used in processing interactions between or among processors in such systems. The disclosed systems and methods provide systems and methods for automatically predicting the accuracy of an abuse report and determining, in accordance with the automatically-determined accuracy of the abuse report, an appropriate action(s) to be taken in response to the abuse report.

Abstract: A relational event history is determined based on a data set, the relational event history including a set of relational events that occurred in time among a set of actors. Data is populated in a probability model based on the relational event history, where the probability model is formulated as a series of conditional probabilities that correspond to a set of sequential decisions by an actor for each relational event, where the probability model includes one or more statistical parameters and corresponding statistics. A baseline communications behavior for the relational event history is determined based on the populated probability model, and departures within the relational event history from the baseline communications behavior are determined.

Abstract: Methods, systems, and devices for semantic parsing. In an example embodiment, a method for semantic parsing can include steps, operations, or instructions such as obtaining a data pair for learning, the data pair comprising logical form data and natural utterance data; acquiring grammar for targeted logical forms among the logical form data of the data pair; modeling data comprising other available prior knowledge utilizing WFSA (Weighted Finite State Automata); combining with the targeted logical forms with the data modeled comprising the other available prior knowledge to form a background; and exploiting the background on the data pair. Note that we do not “learn” the background, but “learn” the background-RNN (Recurrent Neural Network).

Abstract: A thermal displacement compensation apparatus for compensating a dimensional measurement error due to a thermal displacement of a workpiece, including a machine learning device for learning shape measurement data at the time of inspection of the workpiece, wherein the machine learning device observes image data showing the temperature distribution of the workpiece and shape data after machining as state variables representing the current state of the environment, acquires judgment data indicating the shape measurement data at the time of inspection, and learns the image data showing the temperature distribution of the workpiece and shape data after machining and the shape measurement data at the time of inspection in association with each other using the observed state variables and the acquired judgment data.

Abstract: A content for a message to be submitted to a social networking account of a person can be received. The message can be submitted and the content can be shared with other persons via the social network. Prior to conveying, submitting, and/or storing, the message can be scored in one or more dimensions. The dimensions can represent aspects of a reputation of the person. Previously established threshold scores for each of the dimensions can be determined. When the content is outside an established allowance range of the scores, performing a programmatic action to ensure that the submission of the message does not automatically occur to the account. When the content is not outside the scores, not taking a programmatic action to prevent the submission of the message and instead permitting the submission of the message to automatically occur to the account.

Abstract: A cultural determination engine is provided. The cultural determination engine is configured to assess a cultural profile by computing a distance between a received response to a query and a reference response.