Abstract: Disclosed are systems, methods, and other implementations that include a machine-implemented artificial neural network including a plurality of nodes, with the nodes forming at plurality of layers including an input layer, at least one hidden layer, and an output layer, and a plurality of links, with each link coupling a corresponding source node and a receiving node. At least one link is configured to evaluate a piecewise linear function of a value provided by a first source node, from the plurality of nodes, to yield a value for a first receiving node coupled to the at least one link. Each node of a hidden layer is configured to aggregate values provided by links for which that node is the receiving node of the link, with the first receiving node providing non-linear output resulting, in part, from the at least one link configured to evaluate the piecewise linear function.

Abstract: A method for multi-instance learning (MIL)-based classification of a streaming input is described. The method includes running a first biased MIL model using extracted features from a subset of instances received in the streaming input to obtain a first classification result. The method also includes running a second biased MIL model using the extracted features to obtain a second classification result. The first biased MIL model is biased opposite the second biased MIL model. The method further includes classifying the streaming input based on the classification results of the first biased MIL model and the second biased MIL model.

Abstract: The exchange of weight gradients among the processing nodes can introduce a substantial bottleneck to the training process. Instead of remaining idle during the weight gradients exchange process, a processing node can update its own set of weights for the next iteration of the training process using the processing node's local weight gradients. The next iteration of training can be started by using these speculative weights until the weight gradients exchange process completes and a global weights update is available. If the speculative weights is close enough to the weight values from the global weights update, the training process at the processing node can continue training using the results computed from the speculative weights to reduce the overall training time.

Abstract: Methods, systems, and apparatus, including computer-readable media, are described for a hardware circuit configured to implement a neural network. The circuit includes a first memory, respective first and second processor cores, and a shared memory. The first memory provides data for performing computations to generate an output for a neural network layer. Each of the first and second cores include a vector memory for storing vector values derived from the data provided by the first memory. The shared memory is disposed generally intermediate the first memory and at least one core and includes: i) a direct memory access (DMA) data path configured to route data between the shared memory and the respective vector memories of the first and second cores and ii) a load-store data path configured to route data between the shared memory and respective vector registers of the first and second cores.

Abstract: Example methods and apparatus to onboard return path data providers for audience measurement are disclosed herein. Example apparatus disclosed herein to predict return path data quality include a classification engine to compute a first data set of model features from validation tuning data reported from media metering devices and a second data set of model features from return path data reported from return path data devices. The example apparatus also include a prediction engine to train a machine learning algorithm based on the first data set, apply the trained machine learning algorithm to the second data set to predict quality of the return path data reported from the return path data devices, and determine an onboarding status for a return path data provider based on an aggregate predicted quality of the return path data reported from the return path data devices.

Abstract: A method for event identification including receiving event information pertaining to events occurring with respect to a computing environment, each event having a measurement metric; evaluating by a probability function the measurement metric for each event to determine when the measurement metric is above a predetermined probability threshold or below a probability threshold wherein above a probability threshold or below a probability threshold is classified as alarm data; processing the alarm data through a decision tree to determine based on historical data when the alarm data is significant or when the alarm data is not significant and to reduce the number of alarm data to a predetermined number of significant alarm data; and displaying the predetermined number of significant alarm data to a user.

Abstract: A method and system to determine a rating for evaluation of a health care procedure is disclosed. The system includes a user interface accepting a request for a rating of the health care procedure. A database includes input data metrics each related to one of health care provider quality metrics, health care provider cost metrics, health care facility quality metrics, and health care facility quality metrics. A machine learning system is trained to provide a rating target value for the health care procedure based on the neural processing of the data factors. The system evaluates a number of machine learning algorithms to determine the best learning algorithm for a particular rating target value based on test data supplied to the machine learning algorithms. The best learning algorithm for the particular rating target value is used by the system to determine the rating for evaluation.

Abstract: Disclosed is a neural network structure enabling efficient training of the network and a method thereto. The structure is a ladder-type structure wherein one or more lateral input(s) is/are taken to decoding functions. By minimizing one or more cost function(s) belonging to the structure the neural network structure may be trained in an efficient way.

Abstract: Techniques are described herein for training and applying memory neural networks, such as “condensed” memory neural networks (“C-MemNN”) and/or “average” memory neural networks (“A-MemNN”). In various embodiments, the memory neural networks may be iteratively trained using training data in the form of free form clinical notes and clinical reference documents. In various embodiments, during each iteration of the training, a so-called “condensed” memory state may be generated and used as part of the next iteration. Once trained, a free form clinical note associated with a patient may be applied as input across the memory neural network to predict one or more diagnoses or outcomes of the patient.

Abstract: Embodiments for ensemble policy generation for prediction systems by a processor. Policies are generated and/or derived for a set of ensemble models to predict a plurality of target variables for streaming data such that the plurality of policies enables dynamic adjustment of the prediction system. One or more of the policies are updated according to one or more error states of the set of ensemble models.

Abstract: An embodiment includes a method for use in managing a system comprising one or more computers, each computer comprising at least one hardware processor coupled to at least one memory. The method comprises a computer-implemented manager: detecting that the system is in an unhealthy state; determining a set of one or more possible actions to remedy the unhealthy state of the system; selecting at least one action of the set of one or more possible actions; and constructing a service request implementing the selected at least one action; wherein at least one of the detecting, determining, selecting, and constructing is based at least in part on applying a reinforcement learning algorithm.

Abstract: An embodiment includes a method for use in managing a system comprising one or more computers, each computer comprising at least one hardware processor coupled to at least one memory. The method comprises a computer-implemented manager: detecting that the system is in an unhealthy state; determining a set of one or more possible actions to remedy the unhealthy state of the system; selecting at least one action of the set of one or more possible actions; and constructing a service request implementing the selected at least one action; wherein at least one of the detecting, determining, selecting, and constructing is based at least in part on applying a reinforcement learning algorithm.

Abstract: A synapse array of a neuromorphic device is provided. The synapse array may include a pre-synaptic neuron; a row line extending from the pre-synaptic neuron in a row direction; a post synaptic neuron; a column line extending from the post-synaptic neuron in a column direction; and a synapse disposed at an intersection region between the row line and the column line. The synapse may include an n-type ferroelectric field effect transistor (n-FeFET) having a source electrode, a gate electrode and a body; a p-type ferroelectric field effect transistor (p-FeFET) having a source electrode, a gate electrode and a body; and a resistive element having a first node electrically connected to the source electrode of the n-FeFET and electrically connected to the source electrode of the p-FeFET, and the n-FeFET and the p-FeFET are electrically connected in series.

Abstract: A system of classifying devices and/or app instances a new or returning divides attributes generated from observations received from an uncharacterized device/software app into base-fingerprint attributes and predictor attributes, where the two kinds of attributes have different longevities. Predictor attribute tuples from attribute tuples having the same base fingerprint as the base fingerprint corresponding to the uncharacterized device/app, and the predictor attribute tuple corresponding to the uncharacterized device/app are analyzed using a machine learned predictor function to obtain a final fingerprint. Machine learning techniques such as logistic regression, support vector machine, and artificial neural network can provide a predictor function that can decrease the conflict rate of the final fingerprint and, hence, the utility thereof, without significantly affecting the accuracy of classification.

Abstract: Traditionally, forecasting models were developed using pest or disease instances collected through pest or disease surveillance. The present disclosure relates to pest forecasting using historical pesticide usage information thereby obviating need for voluminous and time consuming effort of collecting site specific data. Firstly forecasting models for different pests or diseases of different crops are generated based on historical data on pesticide usage and historical weather data collected for a geo-location under consideration. The model is validated and adapted with the current scenario of pests. Current scenario is captured using image samples sent from the field or farm through participatory sensing platform. The images are then analyzed to extract information like actual pest infestation in the field, severity, if there was infestation and the like. This analyses helps to derive the actual pest infestation instances in the field.

Abstract: Described is a system for feature selection that extends supervised hierarchical clustering to neural activity signals. The system generates, using a hierarchical clustering process, a hierarchical dendrogram representing a set of neural activity data comprising individual neural data elements having neural activity patterns. The hierarchical dendrogram is searched for an optimal cluster parcellation using a stochastic supervised search process. An optimal cluster parcellation of the hierarchical dendrogram is determined that provides a classification of the set of neural activity data with respect to a supervised classifier, resulting in a reduced neural activity feature set. The set of neural activity data is classified using the reduced neural activity feature set, and the classified set of neural activity data is decoded.

Abstract: Dynamic multiscale routing on networks of neurosynaptic cores with a feedback attention beam and short term memory with inhibition of return is provided. In various embodiments, an input topographic map is received at a spiking neuromorphic hardware system. A saliency map is received, associating a saliency value with each of a plurality of regions of the input topographic map. Based on the saliency map, a first of the plurality of regions in order of saliency value is routed. The first of the plurality of regions is suppressed. Based on the saliency map, a predetermined number of the plurality of regions are sequentially routed in order of saliency value.

Abstract: An example electronic device includes a crossbar array, row driver circuitry, and column output circuits for each of the column lines of the crossbar array. The crossbar array may include row lines, column lines, and memristors that each are connected between one of the row lines and one of the column lines. The row driver circuitry may be to apply a plurality of analog voltages to a first node during a plurality of time periods, respectively, and, for each of the row lines, selectively connect the row line to the first node during one of the plurality of time periods based on a digital input vector. The column output circuits may each include: an integration capacitor, a switch that is controlled by an integration control signal, and current mirroring circuitry. The current mirroring circuitry may be to, when the switch is closed, flow an integration current to or from an electrode of the integration capacitor whose magnitude mirrors a current flowing on the corresponding column line.

Abstract: Technologies for automatic discovery and connection to a representational state transfer (REST) interface include a provider computing device communicatively coupled to a REST interface of a Web service hosted by a 3rd party. The provider computing device is configured to analyze a data representation received from a REST interface of a Web service in response to having transmitted an HTTP request to an endpoint of the Web service and determine a pattern of the data representation as a function of the analysis of the data representation. Additionally, the provider computing device is configured to generate one or more possible schemas for the REST interface based on the determined pattern. Additional embodiments are described herein.

Abstract: Electronic sensing systems and methods are disclosed. The electronic sensing system (ESS) receive an olfactory product and one or more smell characteristics of the olfactory product are detected and extracted by identifying a headspace of the olfactory product. A comparison of the extracted smell characteristics with one or more smell characteristics associated with a historic training data stored in a database is performed and a match between the extracted smell characteristics and the one or more smell characteristics associated with the historic training data is determined using machine learning technique(s). Further, the ESS generates a report for the olfactory product comprising at least one of type of the consumable, name of the olfactory product, a status of the olfactory product, an age of the olfactory product, and a decaying index, and classifies the olfactory product into one or more categories based on the report and/or the historic training data.