Abstract: Disclosed herein are systems and method for generating synthetic events. A method may include: monitoring user activity on a website of a conversion entity; collecting, for a monitored user session, first-party data including clickstream information on the website; calculating, using a machine learning algorithm, a prediction score indicative of a likelihood that a user associated with the monitored user session will request an asset depicted on the website after a threshold period of time, wherein the machine learning algorithm is trained using training vectors that map at least website clickstream information from various user sessions to offline asset conversion information collected after the threshold period of time from the various user sessions; in response to determining that the prediction score is greater than a threshold prediction score, generating a synthetic event indicative of the request being made by the user; and transmitting the synthetic event to a content platform.

Abstract: A model variable candidate generation device generating explanatory variable candidates to be used as candidates for an explanatory variable in generation of a prediction model includes: a data input unit inputting analysis data each entry having one or more items and the items having item values; a first item determination unit preliminarily setting properties of the items included in the analysis data as first item properties; a data property determination unit determining data properties being of the analysis data on the basis of the first item properties; a second item determination unit determining properties of the items included in the analysis data as second item properties on the basis of the data properties of the analysis data; and a variable candidate generation unit generating the explanatory variable candidates by selecting from the items or processing the items on the basis of the second item properties.

Abstract: A method of performing an inference task on a knowledge graph comprising semantic triples of entities, wherein entity types are subject, object and predicate, and wherein each semantic triple comprises one of each entity type, using a quantum computing device, wherein a first entity of a first type and a second entity of a second type are given and the inference task is to infer a third entity of the third type. By performing specific steps and choosing values according to specific prescriptions, an efficient and resource-saving method is developed that utilizes the power of quantum computing systems for inference tasks on large knowledge graphs. An advantageous value for a cutoff threshold for a cutoff based on singular values of a singular value tensor decomposition is prescribed, and a sequence of steps is developed in which only the squares of the singular values are of consequence and their signs are not.

Abstract: An apparatus includes a plurality of processing layers coupled in series. Each processing layer in the plurality of processing layers includes a Gaussian unit configured to perform a linear transformation on an input signal including a plurality of optical modes. The Gaussian unit includes a network of interconnected beamsplitters and phase shifters and a plurality of squeezers operatively coupled to the network of interconnected beamsplitters and phase shifters. Each processing layer also includes a plurality of nonlinear gates operatively coupled to the Gaussian unit and configured to perform a nonlinear transformation on the plurality of optical modes. The apparatus also includes a controller operatively coupled to the plurality of processing layers and configured to control a setting of the plurality of processing layers.

Abstract: Various device attributes associated with a current event may be obtained. Similarity metrics may be determined that indicate a degree of similarity between the device attributes that are associated with the current event and stored device attributes that are associated with previous events and previously created fuzzy device identifiers. A fuzzy device identifier may be assigned to the current event based at least in part on a comparison of the similarity metrics with a threshold. If none of the similarity metrics compare favorably with the threshold, then a new fuzzy device identifier may be created for the current event. However, if at least one of the similarity metrics compares favorably with the threshold, then the previously created fuzzy device identifier whose stored device attributes are most similar to the device attributes that are associated with the current event may be assigned to the current event.

Abstract: Embodiments of the present invention provide methods, computer program products, and systems for classification and identification of cancer genes while correcting for sample bias for tumor-derived genomic features as well as other biased features using machine learning techniques. Embodiments of the present invention can be used to receive a set of genes that include a first gene and a subset of synthetic genes that include similar features to the first gene and receive a set of gene labels associated with physiological characteristics. Embodiments of the present invention can estimate probabilities that genes in the set of genes are associated with gene labels in the set of gene labels using a machine learning classifier and estimate an effective probability range for the first gene and each gene label based, at least in part, on the first gene's estimated probabilities and the estimated probabilities of one or more of the synthetic genes.

Abstract: A method for generating data explanations in a recursive cortical network includes receiving a set of evidence data at child feature nodes of a first layer of the recursive cortical network, setting a transformation configuration that directs messaging of evidence data and transformed data between layers of the network, performing a series of transformations on the evidence data according to the transformation configuration, the series including at least one forward transformation and at least one reverse transformation, and outputting the transformed evidence data.

Abstract: Systems, methods and articles of manufacture for are provided for analyzing user behavior in real time by ingesting telemetry data related to a streaming media application; feeding the telemetry data to a machine learning model (MLM) that produces a User Experience (UX) command based on the telemetry data and prior telemetry data received from the content streaming application; selecting content items to provide to the client device based on the telemetry data; determining, based on the telemetry data, whether the client device has sufficient free resources to receive the UX command and the content items in a current time window while providing a predefined level of service; when client device has sufficient free resources to receive the UX command and the content items, encapsulating the UX command with the content items in a content stream; and transmitting the content stream to the client device.

Abstract: Systems and methods for determining one or more measures of interest for optimizing throughput of a catheterization laboratory are provided. A priori medical procedure data relating to a medical procedure to be performed on a patient in a catheterization laboratory is received. One or more measures of interest are predicted based on the received a priori medical procedure data using a trained machine learning model. The one or more measures of interest include an overall time for performing the medical procedure on the patient in the catheterization laboratory. The one or more predicted measures of interest are output.

Abstract: Aspects of the present disclosure provide for future user device preference prediction based on telecom data. In one aspect, a computer-implemented method includes collecting the telecom data from at least one node of a wireless communication network, where the telecom data includes records for a plurality of occurrences of user interaction with the wireless communication network via a respective current user device. The telecom data is then applied to a predictive model to obtain a prediction of future user device preferences. The prediction of the future user device preferences may include an indication that a user will switch from the respective current user device to another user device for future use with the wireless communication network. The method further includes performing an action with respect to the wireless communication network in response to the prediction of future user device preferences.

Abstract: The present teaching relates to managing computing resources. In one example, information about resource utilization on a computing node is received from the computing node. Available resource on the computing node is determined based on the information. A model generated in accordance with reinforcement learning based on simulated training data is obtained. An adjusted available resource is generated based on the available resource and the model with respect to the computing node. The adjusted available resource is sent to a scheduler for scheduling one or more jobs to be executed on the computing node based on the adjusted available resource.

Abstract: The present disclosure relates generally to the generation and deployment of a machine learning-enabled decision engine (MLDE). The MLDE includes decision options that are composed of a discrete list of selectable options. Further, the MLDE includes data inputs that can be used to influence decisions made by the machine learning models of the MLDE. Controls are applied to the MLDE to overlay and bound the decisioning within guidelines established by an operator of the MLDE. Once the MLDE is established, the MLDE is validated and deployed for use by software applications to make decisions.

Abstract: Systems and methods are provided for training a model using machine learning. An exemplary method may include providing, by the model in a training session, an action to an environment to receive feedback from the environment. The method may also include generating, by a behavior simulator, a plurality of predicted outcomes from the environment resulting from the action. The method may further include training the model, using at least a subset of the predicted outcomes, to generate a set of candidate models. The method may include receiving actual feedback from the environment and determining whether the actual feedback matches one of the predicted outcomes in the subset. Responsive to the determination that the actual feedback matches one of the predicted outcomes in the subset, the method may include using, in a new training session, the candidate model in the set corresponding to the matched predicted outcome.

Abstract: The techniques herein include using an input context to determine a suggested action and/or cluster. Explanations may also be determined and returned along with the suggested action. The explanations may include (i) one or more most similar cases to the suggested case (e.g., the case associated with the suggested action) and, optionally, a conviction score for each nearby cases; (ii) action probabilities, (iii) excluding cases and distances, (iv) archetype and/or counterfactual cases for the suggested action; (v) feature residuals; (vi) regional model complexity; (vii) fractional dimensionality; (viii) prediction conviction; (ix) feature prediction contribution; and/or other measures such as the ones discussed herein, including certainty. The explanation data may be used to determine whether to perform a suggested action.

Abstract: Method and system for assessing the suitability of an entity using a proxy. A description of a behavior associated with a desirable audience is received. A proxy behavior estimated to be characteristic of the desirable audience is selected. The proxy behavior comprises the performance of proxy events related to the consumption of media received by an entity over a network, which can be found in an entity's consumption history. An entity can be assessed for inclusion in a proxy audience, by examining the entity's consumption history for proxy behaviors. A behavioral model is built using a training set comprising the proxy audience. By applying the behavioral model to the consumption history of a specified entity, the specified entity's suitability for selection can be determined. Advantageously, in an embodiment, the invention enables the use of behavioral modeling techniques even when the complete behavior of the desirable audience is not available.

Abstract: The technology described in this document can be embodied in a computer-implemented method that includes receiving identification information associated with a geographic location. The identification information includes one or more features that affect an acoustic environment of the geographic location at a particular time. The method also includes determining one or more parameters representing at least a subset of the one or more features, and estimating at least one acoustic parameter that represents the acoustic environment of the geographic location at the particular time. The at least one parameter can be estimated using a mapping function that generates the estimate of the at least one acoustic parameter as a weighted combination of the one or more parameters. The method further includes presenting, using a user-interface displayed on a computing device, information representing the at least one acoustic parameter estimated for the geographic location for the particular time.

Abstract: A method for quantizing a machine learning model during an inference phase, including determining a normalization factor using a set of floating-point values and a damped value of a damped value sequence; and assigning a quantized value for each floating-point value of the set of floating-point values based on the damped value sequence and the normalization factor.

Abstract: The present application discloses a method, system, and computer system for building a model associated with a dataset. The method includes receiving a data set, the dataset comprising a plurality of keys and a plurality of key-value relationships, determining a plurality of models to build based at least in part on the dataset, wherein determining the plurality of models to build comprises using the dataset format information to identify the plurality of models, building the plurality of models, and optimizing at least one of the plurality of models.

Abstract: A brain machine interface (BMI) to control a device is provided. The BMI has a neural decoder, which is a neural to kinematic mapping function with neural signals as input to the neural decoder and kinematics to control the device as output of the neural decoder. The neural decoder is based on a continuous-time multiplicative recurrent neural network, which has been trained as a neural to kinematic mapping function. An advantage of the invention is the robustness of the decoder to perturbations in the neural data; its performance degrades less—or not at all in some circumstances—in comparison to the current state decoders. These perturbations make the current use of BMI in a clinical setting extremely challenging. This invention helps to ameliorate this problem. The robustness of the neural decoder does not come at the cost of some performance, in fact an improvement in performance is observed.

Abstract: A method and system analyze data in a database. The method and system include defining a plurality of set of rules, wherein each set of rules corresponds to a predictive model, storing the each set of rules corresponding to the predictive model in a library as a user-defined function and calling the user-defined function via a standard sequel language.