Abstract: A trained computer model includes a direct network and an indirect network. The indirect network generates expected weights or an expected weight distribution for the nodes and layers of the direct network. These expected characteristics may be used to regularize training of the direct network weights and encourage the direct network weights towards those expected, or predicted by the indirect network. Alternatively, the expected weight distribution may be used to probabilistically predict the output of the direct network according to the likelihood of different weights or weight sets provided by the expected weight distribution. The output may be generated by sampling weight sets from the distribution and evaluating the sampled weight sets.

Abstract: A trained computer model includes a direct network and an indirect network. The indirect network generates expected weights or an expected weight distribution for the nodes and layers of the direct network. These expected characteristics may be used to regularize training of the direct network weights and encourage the direct network weights towards those expected, or predicted by the indirect network. Alternatively, the expected weight distribution may be used to probabilistically predict the output of the direct network according to the likelihood of different weights or weight sets provided by the expected weight distribution. The output may be generated by sampling weight sets from the distribution and evaluating the sampled weight sets.

Abstract: Neural Networks such as Deep Neural Networks (DNNs) output calibrated probabilities that substantially represent frequencies of occurrences of events. A DNN propagates uncertainty information of a unit of the DNN from an input to an output of the DNN. The uncertain information measures a degree of consistency of the test data with training data used to train a DNN. The uncertainty information of all units of the DNN can be propagated. Based on the uncertainty information, the DNN outputs probability scores that reflect received input data that is substantially different from the training data.

Abstract: A trained computer model includes a direct network and an indirect network. The indirect network generates expected weights or an expected weight distribution for the nodes and layers of the direct network. These expected characteristics may be used to regularize training of the direct network weights and encourage the direct network weights towards those expected, or predicted by the indirect network. Alternatively, the expected weight distribution may be used to probabilistically predict the output of the direct network according to the likelihood of different weights or weight sets provided by the expected weight distribution. The output may be generated by sampling weight sets from the distribution and evaluating the sampled weight sets.

Abstract: A trained computer model includes a direct network and an indirect network. The indirect network generates expected weights or an expected weight distribution for the nodes and layers of the direct network. These expected characteristics may be used to regularize training of the direct network weights and encourage the direct network weights towards those expected, or predicted by the indirect network. Alternatively, the expected weight distribution may be used to probabilistically predict the output of the direct network according to the likelihood of different weights or weight sets provided by the expected weight distribution. The output may be generated by sampling weight sets from the distribution and evaluating the sampled weight sets.

Abstract: Methods, systems and apparatuses, including computer programs encoded on computer storage media, are provided for learning or optimizing an indirect encoding of a mapping from digitally-encoded input arrays to digitally-encoded output arrays, with numerous technical advantages in terms of efficiency and effectiveness.

Abstract: A trained computer model includes a direct network and an indirect network. The indirect network generates a set of weights or a set of weight distributions for the nodes and layers of the direct network. The direct network includes units associated with unit codes representative of the unit's structural position in the direct network. Weight codes are determined for weights of the direct network based on unit codes associated with units connected by the weights. The indirect network generates the set of weights or set of weight distributions based on weight codes associated with weights of the direct network.

Abstract: The technique relates to a system and method for mining frequent and in-frequent items from a large transaction database to provide the dynamic recommendation of items. The method involves determining user interest for an item by monitoring short item behavior of at least one user then selecting a local category, a neighborhood category and a disjoint category with respect to the item clicked by the at least one user based on long term preferences data of a plurality of users of the ecommerce environment thereafter selecting one or more frequent and infrequent items from each of the selected local, neighborhood and disjoint category items and finally generating one or more dynamic recommendations based on the one or more items selected from the local category, the neighborhood category and the disjoint category and the one or more selected frequent and infrequent items.

Abstract: Neural Networks such as Deep Neural Networks (DNNs) output calibrated probabilities that substantially represent frequencies of occurrences of events. A DNN propagates uncertainty information of a unit of the DNN from an input to an output of the DNN. The uncertain information measures a degree of consistency of the test data with training data used to train a DNN. The uncertainty information of all units of the DNN can be propagated. Based on the uncertainty information, the DNN outputs probability scores that reflect received input data that is substantially different from the training data.

Abstract: A trained computer model includes a direct network and an indirect network. The indirect network generates expected weights or an expected weight distribution for the nodes and layers of the direct network. These expected characteristics may be used to regularize training of the direct network weights and encourage the direct network weights towards those expected, or predicted by the indirect network. Alternatively, the expected weight distribution may be used to probabilistically predict the output of the direct network according to the likelihood of different weights or weight sets provided by the expected weight distribution. The output may be generated by sampling weight sets from the distribution and evaluating the sampled weight sets.

Abstract: An algorithm is provided which uses a model-based concept of a cluster and scores items using a score representative of the probability that a given item has been generated from the same distribution as one or more query items. The items are represented by a feature vector xi comprising a plurality of digitally represented features xij the method including: receiving an input identifying the query items; for each of the other items computing a score which is a function of a conditional probability of the feature vectors xij of the query items being generated from the generating distribution formula (I) given that the respective other item is generated from the generating distribution formula (I) and returning a score for each of the other items, a list of some or all of the other items, sorted by their respective score, or a list of n other items which have the highest score.