The present invention is related to a computer-implemented method of training artificial intelligence (AI) systems or rather agents (Maximum Entropy Regularised multi-goal Reinforcement Learning), in particular, an AI system/agent for controlling a technical system. By constructing a prioritised sampling distribution q(.sup.g) with a higher entropy .sub.q(.sup.g) than the distribution p(.sup.g) of goal state trajectories .sup.g and sampling the goal state trajectories .sup.g with the prioritised sampling distribution q(.sup.g) the AI system/agent is trained to achieve unseen goals by learning from diverse achieved goal states uniformly.

An autonomous vehicle, system and method of operating the autonomous vehicle. The system includes a sensor, a reasoning engine and a navigation system. The sensor receives token data. The reasoning engine performs an abductive inference on a fact determined from the token data to estimate a backward condition, and a deductive inference to the estimated backward condition in to order to predict a forward condition. The navigation system operates the autonomous vehicle based on the predicted forward condition.

A predictive model pipeline data store may contain electronic records defining a predictive model pipeline composed of operation nodes. Based on the information in the data store, an execution framework platform may calculate a hash value for each operation node by including all recursive dependencies using ancestor node hash values and current node parameters. The platform may then compare each computed hash value with a previously computed hash value associated with a prior execution of a prior version of the pipeline. Operation nodes that have an unchanged hash value may be tagged idle. Operation nodes that have a changed hash value may be tagged train and apply or apply based on current node parameters (and an apply tag may propagate backwards through the pipeline to ancestor nodes). The platform may then ignore the operation nodes tagged idle when creating a physical execution plan to be provided to a target platform.

A method of discovering and presenting associations between events includes discovering causal association scores for pairs of events in an event dataset, and generating a sequence of events based on the causal association scores.

In one aspect, a computerized method of computer vision based dynamic universal fashion ontology fashion rating and recommendations includes the step of receiving one or more user-uploaded digital images. The method includes the step of implementing an image classifier on the one or more user-uploaded digital images, to classify a set of user-uploaded fashion content of the one or more user-upload digital images. The method includes the step of receiving a set of fashion rules input by a domain expert. The set of rules determine a set of apparel to match with the set of user-uploaded fashion content, generating a dynamic universal fashion ontology with the image classier and a text classier. The dynamic universal fashion ontology comprises an ontology of set of mutually exclusive attribute classes. The method includes the step of using the dynamic universal fashion ontology to train a specified machine learning based fashion classifications. The method includes the step of using an active learning pipeline to keep the universal fashion ontology up-to-date. The method includes the step of using graphical representation and game theory-based algorithm for outfit generation. The method includes the step of providing an automatic outfit generator, wherein the automatic outfit generator: based on the set of user-uploaded fashion content that is output by the image classifier, matches the set of user-uploaded fashion with a ranked set of apparel suggestions that are based on the set of fashion rules and the specified machine learning based fashion classifications, wherein the automatic outfit generator implements a greedy algorithm to determine the most optimal path in the specified machine learning based fashion classifications to generate each suggested piece of apparel in the ranked set of apparel suggestions. The method includes the step of, based on the highest ranked suggested piece of apparel in the ranked set of apparel suggestions, generating an outfit suggestion. The method includes the step of ranking based on lifestyle parameters including but not limited to weather, brand affinity, brand popularity and novelty of style.

A abductive inference apparatus (1) includes a candidate hypothesis generation unit (2) configured to apply, to an observation that indicates an observed situation using a logical expression, inference knowledge provided with the reliability for making a forward inference and the reliability for making a reverse inference, make an inference, and generate a candidate hypothesis by which the observation can be derived; and a candidate hypothesis evaluation unit (3) configured to specify an inference direction for each piece of the inference knowledge applied to the generated candidate hypothesis, and calculate an evaluation value of the candidate hypothesis using the reliability of each piece of the inference knowledge that corresponds to the specified inference direction.

A system for event prediction using schema networks includes a first antecedent entity state that represents a first entity at a first time; a first consequent entity state that represents the first entity at a second time; a second antecedent entity state that represents a second entity at the first time; and a first schema factor that couples the first and second antecedent entity states to the first consequent entity state; wherein the first schema factor is configured to predict the first consequent entity state from the first and second antecedent entity states.

Systems and methods for automatically determining target populations for statistical experiments are disclosed. The system may receive a hypothesis associated with a statistical experiment and a target population, the hypothesis including one or more target metrics. The system may receive one or more target parameters associated with the target population. The system may determine whether the one or more target parameters match a stored query. In response to the target parameters matching the stored query, the system may query, using the stored query, a user database to determine the target population satisfying the target parameters. The system may predict a sample size for the statistical experiment based on the target population and the target metrics and transmit to the user device a graphical user interface including the predicted sample size.

In an example, in response to occurrence of a report generation event, a report may be generated. An aspect of the report requiring a description may be identified, the aspect being at least one of a trend noted in the report and a discrepancy in the report. A hypothesis explaining the aspect of the report may be generated. Further, an evidence may be collected for the hypothesis, based on a relation between entities of the hypothesis, the relation being determined based on a knowledge data having information pertaining to the entities. The hypothesis may be evaluated generate an evaluation score, based on the collected evidence. Based on the evaluation score, the hypothesis may be selected for explaining the aspect. The selected hypothesis may be provided in natural language text explaining the aspect of the report, based on at least one of the domain and user knowledge and linguistic knowledge.

The disclosure provides an information processing method and device. In one embodiment, an information processing method comprises receiving a request for generating questions inputted by a user, the request for generating questions includes a to-be-learned knowledge point; acquiring, from a knowledge graph for questions, a node path including a target node indicating the to-be-learned knowledge point, the nodes in the knowledge graph for questions indicating question-answering steps of existing questions, knowledge points tested in the question-answering steps, and questioning styles corresponding to the question-answering steps; and generating questions required by the user according to question-answering steps, knowledge points tested in the question-answering steps, and questioning styles corresponding to the question-answering steps indicated by nodes on the node path. The present disclosure enables generation of new questions and facilitates the expansion of a question bank.