Abstract: Various embodiments are generally directed to an apparatus, method and other techniques to receive a biometric input of a first input type, determine a distinctiveness value for the biometric input based on a comparison of an attributes score for the biometric input with an average of attributes scores for biometric inputs of the first input type from the plurality of biometric inputs, and determine an input type to use to perform an action based on the distinctiveness value.

Abstract: A chatbot can use a knowledge base including question/answer pairs to respond to questions. When a question is asked that does not correspond to a question/answer pair in the knowledge base, the chatbot can send the question to one or more humans to obtain an answer. However, only some people will have the experience, context, knowledge, etc., to answer the question. A model can be trained to select “experts” that are likely to be able to provide a good answer to a question by using both A) a vector comprising characteristics of questions and of the person posing the questions and B) a vector comprising characteristics of a possible expert. The model can trained to produce a value predicting how good an identified expert's answer is likely to be. The model can be trained based on measures of past answers provided for types of questions/questioners.

Abstract: An analytics engine operates on data associated with users and opportunities. A broker system provides the opportunity data to the analytics engine, but the analytics engine does not provide user data to the broker system. The analytics engine notifies users of results of analytics operations.

Abstract: A computer-implemented method of treating a patient's and automated enteral feeding, comprising: monitoring a plurality of reflux-related parameters and at least one reflux event while the patient is automatically enterally fed by an enteral feeding controller according to a baseline feeding profile including a target nutritional goal, training a classifier component of a model for predicting likelihood of a future reflux event according to an input of scheduled and/or predicted plurality of reflux-related parameters, the classifier trained according to computed correlations between the plurality of reflux-related parameters and the at least one reflux event, feeding scheduled and/or predicted reflux-related parameters into the trained classifier component of the model for outputting risk of likelihood of a future reflux event, and computing, by the model, an adjustment to the baseline feeding profile for reducing likelihood of the future reflux event and for meeting the target nutritional goal.

Abstract: Disclosed embodiments are related to feature hashing techniques. A processing device of a database system may identify a set of machine learning features; generate a first hash map of said set of machine learning features and a second different hash map of said set of machine learning features. The processing device may generate a memory compact model for an online machine learning system using the first and second hash maps, and store the memory compact model in the memory device.

Abstract: Systems and methods disclosed herein compactly store representations of segment-specific interaction data from a real time data stream of data interactions by multiple entities to facilitate segment-specific analytics for particular time periods. Segment rules defining characteristics of entities within a segment are received. A first probabilistic data structure is created representing unique entity IDs included in instances of interaction data in the real time data stream during a first time period. A second probabilistic data structure representing unique entity IDs included in instances of interaction data in the real time data stream during a second time period different from the first time period. The first probabilistic data structure represents only entity IDs of entities within the segment and the second probabilistic data structure represents only entity IDs of entities within the segment. The first and second probabilistic data structures are indexed and stored.

Abstract: An identity and access management IAM system is augmented to provide for supervised, iterative machine learning (ML), preferably with a user-generated training set for classification. The training set may include various types of data, including characteristics or attributes of the account types, the users, or the like. A goal of the initial ML training, which may include one or multiple passes, is to enable the machine to identify specific characteristics or attributes that provide a good classification result, with the resulting classifications then applied within the IAM system. In particular, the output of the ML system may be used by the IAM system for enforcing rights associated with the identified accounts, managing accounts, and so forth.

Abstract: A machine learning method includes installing a plurality of model replicas for training on a plurality of computer learning nodes; receiving training data at a each model replica and updating parameters for the model replica after trailing; sending the parameters to other model replicas with a communication batch size; evaluating received parameters from other model replicas; and dynamically adjusting the communication batch size to balance computation and communication overhead and ensuring convergence even with a mismatch in processing abilities on different computer learning nodes.

Abstract: A system and method for content generation and targeting using machine learning are provided. In example embodiments, a probability that a user will visit a webpage based on historical data is calculated. A probability that the user will engage with a particular content category based on past user engagement is calculated. In response to the probability of the user engaging with the particular content category being equal to or greater than a first threshold, the content is generated. Further, in response to the probability of the user not visiting a webpage meeting or exceeding a second threshold, the generated content is sent to the user.

Abstract: A device may perform an iteration of an optimization procedure. The device may apply a smoothing technique to a value relating to the optimization procedure after performing the iteration of the optimization procedure. The device may selectively terminate the optimization procedure based on applying the smoothing technique to the value relating to the optimization procedure. The device may provide information identifying a result of the optimization procedure based on selectively terminating the optimization procedure.

Abstract: Described is a system for storing and retrieving a memory in context. A memory formed for a given context is encoded in a neural model of the entorhinal-hippocampal system, forming a context-appropriate memory. The context-appropriate memory is comprised of an association between presented environmental cues and presence of a rewarded event. The system is able to discriminate between environmental cues in an environment surrounding a vehicle and retrieve at least one encoded context-appropriate memory. Using the at least one retrieved encoded context-appropriate memory, the system determines whether to initiate a collision avoidance operation to cause the vehicle to proactively avoid a collision.

Abstract: Embodiments include identifying unusual activity in an IT system based on user configurable message anomaly scoring. Aspects include receiving a message stream for the IT system and dividing the message stream into a plurality of intervals, wherein each interval corresponds to a time period. Aspects also include identifying and removing one or more intervals from the plurality of intervals that include a startup or a shutdown of an element of the IT system, identifying and removing one or more intervals from the plurality of intervals that correspond to a standard level of command activity and an elevated level of user complaint activity, and identifying and removing one or more intervals from the plurality of intervals that correspond to an elevated level of command activity and an standard level of user complaint activity. Aspects further include creating a training set of intervals that consists of the remaining labelled intervals.

Abstract: A method for establishing sensorimotor programs includes specifying a concept relationship that relates a first concept to a second concept and establishes the second concept as higher-order than the first concept; training a first sensorimotor program to accomplish the first concept using a set of primitive actions; and training a second sensorimotor program to accomplish the second concept using the first sensorimotor program and the set of primitive actions.

Abstract: A mobile device receives ranked news feed stories from a server of a social networking system. The mobile device determines whether to adjust the ranking based on local information generated by applications executing on the mobile device or hardware of the mobile device. Examples of local information of the mobile device include information describing the mobile devices' network connection, geographical location, sensor readings, downloaded data on memory storage, and interactions of software applications executing on the mobile device. For example, if a network co-processor of a mobile device detects a slow network connection, the mobile device lowers the ranking of news feed stories expected to require further use of network bandwidth.

Abstract: In an example method, a mobile device receives a first calendar item associated with a first event. The first calendar item includes a first text string. The mobile device determines a correlation between the first text string and one or more locations associated with one or more second events. The mobile device determines a suggested location for the first event based on the correlation.

Abstract: The present invention relates generally to identifying relationships between items. Certain embodiments of the present invention are configurable to identify the probability that a certain event will occur by identifying relationships between items. Certain embodiments of the present invention provide an improved supervised machine learning system.

Abstract: A method for implementing a convolutional neural network (CNN) accelerator on a target includes utilizing one or more processing elements to implement a standard convolution layer. A configuration of the CNN accelerator is modified to change a data flow between components on the CNN accelerator. The one or more processing elements is utilized to implement a fully connected layer in response to the change in the data flow.

Abstract: Disclosed herein is a computer-implemented tool that facilitates data analysis by use of machine learning (ML) techniques. The tool cooperates with a data intake and query system and provides a graphical user interface (GUI) that enables a user to train and apply a variety of different ML models on user-selected datasets of stored machine data. The tool can provide active guidance to the user, to help the user choose data analysis paths that are likely to produce useful results and to avoid data analysis paths that are less likely to produce useful results.

Abstract: A method and a system for predicting admission of a human subject to a first ward in a medical center are disclosed. A patient dataset is generated based on at least a measure of one or more physiological parameters associated with one or more first human subjects and a first information pertaining to the admission of each of the one or more first human subjects to the first ward. For a first human subject of the one or more first human subjects, a first score at each of the one or more first time instants is determined. Further, one or more second time instants from the one or more first time instants are identified. Further, a second score at each of the one or more second time instants is determined. In an embodiment, the first classifier is trained based on at least the second score, and the first information.

Abstract: A mechanism is provided for modifying an existing recipe to meet a set of desired colors for a final food dish. Responsive to receiving a request to modify the existing recipe to meet the set of desired colors, at least one of the set of existing colors to be changed to meet the desired set of colors is identified. An ingredient-action-sequence triplet associated with each at least one existing color to be changed in the existing recipe is identified and, from a corpus of ingredient-action-sequence triplets associated with other existing recipes, one or more candidates that can be added to produce the at least one target color are identified. The one or more candidates that can be added are ranked based on how each candidate pairs best with other ingredients in the existing recipe. Based on a selection of a candidate, the existing recipe is modified with the selected candidate.