Consciousness is widely considered to be a mysterious and uniquely human trait, which cannot be achieved artificially. On the contrary, a system and method are disclosed for a computational machine that can recognize itself and other agents in a dynamic environment, in a way that seems quite similar to biological consciousness in humans and animals. The machine comprises an artificial neural network configured to identify correlated temporal patterns and attribute causality and agency. The machine is further configured to construct a virtual reality environment of agents and objects based on sensor inputs, to create a coherent narrative, and to select future actions to pursue goals. Such a machine may have application to enhanced decision-making in autonomous vehicles, robotic agents, and intelligent digital assistants.

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.

Systems and methods for operating a communication device. The methods comprise: receiving a signal at the communication device; performing, by the communication device, one or more machine learning algorithms using at least one feature of the signal as an input to generate a plurality of scores (each score representing a likelihood that the signal was modulated using a given modulation type of a plurality of different modulation types); assigning a modulation class to the signal based on the plurality of scores; determining whether a given wireless channel is available based at least on the modulation class assigned to the signal; and selectively using the given wireless channel for communicating signals based on results of the determining.

A method of improving computing efficiency of a computing device for language-independent problem solving and reasoning includes receiving a query from a user, which is decomposed into one or more sub-queries arranged according to a tree structure. The one or more sub-queries are executed in a knowledge base. The results of the executed one or more sub-queries are received and composed into a query response. The query response is transmitted to the user.

A computing system identifies broadcast video for a plurality of games in a first league. The broadcast video includes a plurality of video frames. The computing system generates tracking data for each game from the broadcast video of a corresponding game. The computing system enriches the tracking data. The enriching includes merging play-by-play data for the game with the tracking data of the corresponding game. The computing system generates padded tracking data based on the tracking data. The computing system projects player performance in a second league for each player based on the tracking data and the padded tracking data.

Learning disentangled representations is an important topic in machine learning for a wide range of applications. Disentangled latent variables represent interpretable semantic information and reflect separate factors of variation in data. Although generative models may learn latent representations and generate data samples as well, existing models may ignore the structural information among latent representations. Described in the present disclosure are embodiments to learn disentangled latent structural representations from data using decomposable variational auto-encoders, which simultaneously learn component representations and encode component relationships. Embodiments of a novel structural prior for latent representations are disclosed to capture interactions among different data components. Embodiments are applied to data segmentation and latent relation discovery among different data components. Experiments on several datasets demonstrate the utility of the present model embodiments.

An apparatus, a program-stored storage medium and a method with an inference engine can execute inference using a minimum ruleset in various applications. The apparatus includes: a machine learning engine being a classifying-type engine configured to include adapted-to-category learning models each generated by using each adapted-to-category set of teacher data, the adapted-to-category set being obtained by classifying teacher data for each category, and to use the learning models to output a category data corresponding to the inputted object data; a ruleset selector configured to select, from rulesets each prepared for each category and stored in a rule base, a ruleset corresponding to the category data outputted from the machine learning engine; and a rule engine configured to execute inference to the inputted object data by using the ruleset selected by the ruleset selector, and to output the inference result.

This disclosure relates to improved techniques for performing human parsing functions using neural network architectures. The neural network architecture can model human objects in images using a hierarchal graph of interconnected nodes that correspond to anatomical features at various levels. Multi-level inference information can be generated for each of the nodes using separate inference processes. The multi-level inference information for each node can be combined or fused to generate final predictions for each of the nodes. Parsing results may be generated based on the final predictions.

Systems and methods for operating a communication device. The methods comprise: receiving a signal at the communication device; performing, by the communication device, one or more machine learning algorithms using at least one feature of the signal as an input to generate a plurality of scores (each score representing a likelihood that the signal was modulated using a given modulation type of a plurality of different modulation types); assigning a modulation class to the signal based on the plurality of scores; determining whether a given wireless channel is available based at least on the modulation class assigned to the signal; and selectively using the given wireless channel for communicating signals based on results of the determining.

Disclosed is an optimization decision-making method of an industrial process fusing domain knowledge and multi-source data. The method comprises the steps of: acquiring the domain knowledge of the industrial process by using probability soft logic, and building an domain rule knowledge base of the industrial process; fusing multi-source data semantics and multi-source data features to form a new semantic knowledge representation of the industrial process, and constructing a semantic knowledge base of the industrial process; under a posteriori regularization framework, utilizing the domain rule knowledge base of the industrial process and the semantic knowledge base of the industrial process to obtain an optimization decision-making model embedded with the domain rule knowledge and obtain a posteriori distribution model; and migrating knowledge in the optimization decision-making model embedded with the domain rule knowledge into the posteriori distribution model through the knowledge distillation technology.