Abstract: A configuration mapping system and method increase the effectiveness of mapping of information from an established product line to a new product offering. In at least one embodiment, the configuration mapping system herein uses configuration mapping rules to map individual product features and entire configurations from established products to a new product offering. The configuration mapping system also provides a way to appropriately map, for example, demand and sales information for the purpose of demand estimation and sales prediction. Conventionally, mapping can be ineffective because the configuration mapping rules usually focus on one part of the product at a time, and, if applied in isolation, the impact on other parts is missed. The systems and method herein provide a way to integrate configuration mapping rules across feature parts, time periods, and product lines into a unified, holistic view, allowing for new insights.

Abstract: A method for training a neural network includes receiving labeled training data at a master node, generating, by the master node, partitioned training data from the labeled training data and a held-out set of the labeled training data, determining a plurality of gradients for the partitioned training data, wherein the determination of the gradients is distributed across a plurality of worker nodes, determining a plurality of curvature matrix-vector products over the plurality of samples of the partitioned training data, wherein the determination of the plurality of curvature matrix-vector products is distributed across the plurality of worker nodes, and determining, by the master node, a second-order optimization of the plurality of gradients and the plurality of curvature matrix-vector products, producing a trained neural network configured to perform a structured classification task using a sequence-discriminative criterion.

Abstract: Improved decision tree training in machine learning is described, for example, for automated classification of body organs in medical images or for detection of body joint positions in depth images. In various embodiments, improved estimates of uncertainty are used when training random decision forests for machine learning tasks in order to give improved accuracy of predictions and fewer errors. In examples, bias corrected estimates of entropy or Gini index are used or non-parametric estimates of differential entropy. In examples, resulting trained random decision forests are better able to perform classification or regression tasks for a variety of applications without undue increase in computational load.

Abstract: The current application is directed to methods, and to systems employing the methods, that allow built-in indexing methods for facts, to additionally be applied to rules within a logic-programming system. The methods and systems to which the current application is directed convert an original set of rules into an equivalent set of fact/rule pairs. In addition, a new set of rules may be directly encoded as a new set of fact/rule pairs by these methods and systems. The equivalent set of fact/rule pairs implement the original set of rules, preserving the meaning of the original rules, but the equivalent set of fact/rule pairs are indexed by built-in indexing methods for facts. The new fact/rule pairs are also indexed by built-in indexing methods for facts.

Abstract: Techniques are disclosed for normalizing and publishing alerts using a behavioral recognition-based video surveillance system configured with an alert normalization module. Certain embodiments allow a user of the behavioral recognition system to provide the normalization module with a set of relative weights for alert types and a maximum publication value. Using these values, the normalization module evaluates an alert and determines whether its rareness value exceed a threshold. Upon determining that the alert exceeds the threshold, the module normalizes and publishes the alert.

Abstract: A system, method, and computer product for reducing volume of transmissions of measurements of affective response are described herein. In one embodiment, an interaction analyzer receives a description of an interaction of a user with a media controller that controls presentation of content to the user. The interaction analyzer identifies from the description an action that causes a deviation from a progression of presentation of the content that would have occurred had the action not taken place. A transmitter sends a request to transmit measurements of affective response, taken by a sensor, during a window during which the user likely expressed an affective response related to the action. In some embodiments, the request is received by a transceiver coupled to the sensor with memory sufficient to store measurements of affective response of the user taken since the start of the window, which precedes the time the request is sent.

Abstract: A computer-implemented method for layered training of machine-learning architectures includes receiving a plurality of data elements wherein each data element is associated with a timestamp, determining a training window for each model layer of a layered stack of model layers, determining a plurality of training data elements for each training window by identifying the data elements with timestamps corresponding to each of the training windows, identifying a previous checkpoint for each model layer wherein the previous checkpoint for each model layer is generated by a parent model layer, training each model layer with the determined training data elements for each model layer and the identified previous checkpoint for each model layer, generating a plurality of current checkpoints wherein each current checkpoint of the plurality of current checkpoints is associated with a model layer, and storing the plurality of current checkpoints at the memory.

Abstract: In some example embodiments, a system and method are provided for graph pattern analysis. In example embodiments, pattern data of a primary network that includes data relating to relationships between entities are received. A secondary network based on the pattern data of the primary network is generated by using an algorithm that processes pattern characteristics extracted from the pattern data. The generated secondary network is provided for further analysis.

Abstract: Systems and methods are disclosed for classifying histological tissues or specimens with two phases. In a first phase, the method includes providing off-line training using a processor during which one or more classifiers are trained based on examples, including: finding a split of features into sets of increasing computational cost, assigning a computational cost to each set; training for each set of features a classifier using training examples; training for each classifier, a utility function that scores a usefulness of extracting the next feature set for a given tissue unit using the training examples.

Abstract: Described herein are systems, methods, and computer program products for collecting naturally expressed affective responses for training an emotional response predictor utilizing voting on content. In one embodiment, a label generator is configured to receive a vote, provided by a user, on a segment of content consumed by the user. The label generator determines whether the user consumed the segment during a duration that is shorter than a predetermined threshold, and utilizes the vote to generate a label related to an emotional response to the segment. A training module receives the label and measurement of an affective response of the user taken, at least in part, during a period that starts at most 30 seconds before the vote is provided, and trains the emotional response predictor with the measurement and the label.

Abstract: Methods, systems and computer program products for evaluating performance of generative models are disclosed. One method includes providing a base model and a candidate model having observed variables and first and second conceptually related variables related to the observed variables, respectively, receiving observations assigned to a subset of the observed variables, and for each observation, evaluating the observation by the base model to produce a base assessment of the observation, evaluating the observation by the candidate model to produce a second assessment of the observation, determining a similarity measure of the assessment of the observation based on the base and second assessments, and selecting a subset of observations having low similarity measures for use in evaluating performance of the candidate model.

Abstract: A method, apparatus and computer program product for providing sparse class representation with linear programming is provided. A first model is built using a positive data set. A second model is built using a negative data set. Linear programming is used to distinguishing the first model from the second model to determine a set of salient features for a filter for use as an image classifier.

Abstract: An apparatus and method for calculating an internal state for artificial emotions are disclosed, of which the method comprises multiplying an input value obtained from a sensor with a first personality set in accordance with at least one low rank element contained in at least one high rank element of a NEO PI-R (Revised NEO Personality Inventory); calculating a personality factor value in a Five-Factor Model of the personality by adding the results of the multiplication; and calculating the internal state by multiplying the personality factor value with a second personality.