Various embodiments may be generally directed to the use of an adversarial learning framework for persona-based dialogue modeling. In some embodiments, automated multi-turn dialogue response generation may be performed using a persona-based hierarchical recurrent encoder-decoder-based generative adversarial network (phredGAN). Such a phredGAN may feature a persona-based hierarchical recurrent encoder-decoder (PHRED) generator and a conditional discriminator. In some embodiments, the conditional discriminator may include an adversarial discriminator that is provided with attribute representations as inputs. In some other embodiments, the conditional discriminator may include an attribute discriminator, and attribute representations may be handled as targets of the attribute discriminator. The embodiments are not limited in this context.

A fraud detection system is disclosed that detects potential fraudulent behavior associated a user account by identifying attributes of the user account that share attributes with one or more known fraudulent user accounts. The set of shared attributes for a user account are identified by constructing a bipartite graph comprising a set of user account nodes and a set of attribute nodes associated with the set of user account nodes. A match score for the user account is computed based on the set of shared attributes. Actions to be taken for the user account are identified based on the match score. The actions may include tagging the user account as potentially fraudulent. The actions can be used by a user (e.g., an administrator) of an organization to more intelligently determine appropriate measures to be taken for the potentially fraudulent user account.

Provided herein are a method and device for detection of anomalous instructions sent from a controller of a medical device, to be received by a medical device. The method and the device utilize a dual layer architecture including a first, unsupervised detection layer and a second, supervised detection layer, wherein the layers are applied to the received instructions in series to efficiently detect anomalous instruction prior to the instructions reaching the medical device.

A method of utilizing an artificial intelligence, AI, having language recognition software allowing the AI to have humanistic characteristics while interacting with an online shopper. The AI interacts with a multiplicity of online shoppers concurrently and in real time to determine the validity of the shopper's contact information and the shopper's level of interest in the product. The AI will again interact with the multiplicity of shoppers, concurrently and in real time, and interact with the shoppers and the appropriate salespersons to make connections between the online shoppers and the salespersons within minutes of the online shoppers engaging in an online conversation with the AI. If either the shopper or the salesperson in any single interaction is unavailable, then the AI will attempt to schedule a future connection between the shopper and a salesperson. The AI will continue to follow up between the online shopper and salespersons until a connection is made or the online shopper indicates they are no longer interested.

Automatically mapping and combining the application of machine learning models to answer queries according to semantic specification. A query is parsed to extract keywords from the query and to contextualize the query. Based on the keywords, machine learning models are selected that process concepts associated with the keywords. The machine learning models are sorted according to the contextualization of the query. The machine learning models are run on multimodal data according to a sorted order, where data resulting from an output of one of the machine learning models is used as input to another one of the machine learning models. A query result is output based on a result from running the machine learning models.

A system and method for generating a response to a user query. The method encompasses receiving, at a transceiver unit [102], the user query. The method thereafter leads to identifying, by an encoder unit [104], a user context associated with the user query based on one or more pre-stored datasets. Further the method encompasses predicting, by a prediction unit [106], one or more parameters corresponding the user query based on at least one of one or more offline-policies and one or more online-policies. The method thereafter comprises generating, by a decoder unit [108], the response to the user query based at least on the user context associated with the user query and the one or more parameters corresponding to the user query.

A method learns approximate translations of unfamiliar measurement units during deep question answering (DeepQA) system training and usage. The DeepQA system receives a training set containing Question-Answer (QA) pairs having known unit-of-measurement terms, where each QA pair contains an answer having a known numeric value for a corresponding question from the QA pair. The DeepQA system receives a question from each QA pair from the training set to the DeepQA system in order to find answers and passage phrases to the question from each QA pair, and then identifies all found answers and passage phrases having values that are within a predetermined range of answer values of the training set, where one or more of the identified all found answers and passage phrases contain unfamiliar unit-of-measurement terms, in order to learn approximate translations of the unfamiliar unit-of-measurement terms.

Provided are a method of training a neural network for calculating a learning ability and a method of calculating a user's learning ability. The method of training a neural network includes acquiring an assessment database including data, which includes question information answered by a user at a second time point earlier than a first time point, the user's answer information to the question information, and the user's score information in a second assessment system, acquired from the second assessment system different from a first assessment system, generating an answer sequence from the assessment database by matching the answer information with the score information to prepare a training set, preparing a neural network for calculating the user's score information in the second assessment system on the basis of the answer information in the second assessment system, and training the neural network with the training set.

An approach for a non-factoid question answering framework across tasks and domains may be provided. The approach may include training a multi-task joint learning model in a general domain. The approach may also include initializing the multi-task joint learning model in a specific target domain. The approach may include tuning the joint learning model in the target domain. The approach may include determining which task of the multiple tasks is more difficult for the multi-task joint learning model to learn. The approach may also include dynamically adjusting the weights of the multi-task joint learning model, allowing the model to concentrate on learning the more difficult learning task.

System and method for amplifying the accuracy of forecasts generated by software systems that harness the collective intelligence of human populations by curating optimized sub-populations through an intelligent selection process. Participants predict event outcomes and/or provide evaluations of their confidence in their predictions. The system determines a score wherein the alignment score indicates how well that participant's prediction aligns with the predictions given by the baseline population. Participants can then be selected from the population based on the participant alignment scores.