Abstract: Systems and method are disclosed for determining complex interactions among system inputs by using semi-Restricted Boltzmann Machines (RBMs) with factorized gated interactions of different orders to model complex interactions among system inputs; applying semi-RBMs to train a deep neural network with high-order within-layer interactions for learning a distance metric and a feature mapping; and tuning the deep neural network by minimizing margin violations between positive query document pairs and corresponding negative pairs.

Abstract: Systems and methods are disclosed to answer free form questions using recursive neural network (RNN) by defining feature representations at every node of a parse trees of questions and supporting sentences, when applied recursively, starting with token vectors from a neural probabilistic language model; and extracting answers to arbitrary natural language questions from supporting sentences.

Abstract: Systems and methods are disclosed for representing a word by extracting n-dimensions for the word from an original language model; if the word has been previously processed, use values previously chosen to define an (n+m) dimensional vector and otherwise randomly selecting m values to define the (n+m) dimensional vector; and applying the (n+m) dimensional vector to represent words that are not well-represented in the language model.

Abstract: Systems and methods are disclosed to perform preference learning on a set of documents includes receiving raw input features from the set of documents stored on a data storage device; generating polynomial combinations from the raw input features; generating one or more parameters; applying the parameters to one or more classifiers to generate outputs; determining a loss function and parameter gradients and updating parameters determining one or more sparse regularizing terms and updating the parameters; and expressing that one document is preferred over another in a search query and retrieving one or more documents responsive to the search query.

Abstract: Semantic indexing methods and systems are disclosed. One such method is directed to training a semantic indexing model by employing an expanded query. The query can be expanded by merging the query with documents that are relevant to the query for purposes of compensating for a lack of training data. In accordance with another exemplary aspect, time difference features can be incorporated into a semantic indexing model to account for changes in query distributions over time.

Abstract: Systems and methods are disclosed to perform preference learning on a set of documents includes receiving raw input features from the set of documents stored on a data storage device; generating polynomial combinations from the raw input features; generating one or more parameters; applying the parameters to one or more classifiers to generate outputs; determining a loss function and parameter gradients and updating parameters determining one or more sparse regularizing terms and updating the parameters; and expressing that one document is preferred over another in a search query and retrieving one or more documents responsive to the search query.

Abstract: Systems and methods are disclosed to perform preference learning on a set of documents includes receiving raw input features from the set of documents stored on a data storage device; generating polynomial combinations from the raw input features; generating one or more parameters; applying the parameters to one or more classifiers to generate outputs; determining a loss function and parameter gradients and updating parameters determining one or more sparse regularizing terms and updating the parameters; and expressing that one document is preferred over another in a search query and retrieving one or more documents responsive to the search query.

Abstract: A cell phone having distributed artificial intelligence services is provided. The cell phone includes a neural network for performing a first pass of object recognition on an image to identify objects of interest therein based on one or more criterion. The cell phone also includes a patch generator for deriving patches from the objects of interest. Each of the patches includes a portion of a respective one of the objects of interest. The cell phone additionally includes a transmitter for transmitting the patches to a server for further processing in place of an entirety of the image to reduce network traffic.

Abstract: A wireless power supply system and a self adaptive regulation method thereof. The method includes the following steps: detecting an operating mode of an electric power sending unit (210); judging whether the electric power sending unit coincides with a normal operation condition of the wireless power supply system (200) according to the detected operating mode; determining according to a judging result whether to regulate a main oscillating frequency of an oscillating circuit (213) or not, so as to make the main oscillating frequency of the oscillating circuit be maintained between the resonant frequency of a sending coil (214) and the resonant frequency of a receiving coil (221).

Abstract: An electronic device (100), a wireless power supplying system (10) thereof and a wireless power supplying method thereof. The electronic device (100) includes an internal function circuit (30) and the wireless power supplying system (10). The wireless power supply system (10) includes a wireless electric power transmitter (11), a wireless electric power receiver (12) and a power supply detection unit (13). The wireless electric power transmitter (11) includes transmitter control module (111) and a transmitter power supplying module (112). The wireless electric power receiver (12) receives the electric power from the transmitter power supplying module (112). The power supply detection unit (13) includes an electric power detection module (131), a processor (132) and an alarm module (133). The electric power detection module (131) detects an operating voltage received from the wireless electric power receiver (12); and the processor (132) compares the operating voltage with a preset operating voltage range.

Abstract: An electronic device, and a power supplying method and a wireless power supplying system thereof. The electronic device includes a wired electric power receiving module, a wireless electric power receiving module and a switch. The wired electric power receiving module is connected to an external power supply by wired transmission. The wireless electric power receiving module receives the wireless electric power from an external wireless electric power transmitting device. The switch is coupled to the wired electric power receiving module and the wireless electric power receiving module and is used to switch between the wired electric power receiving module and the wireless electric power receiving module, to supply the operating voltage. The electronic device can operate in the wireless power supplying mode or the wired power supplying mode, so as to facilitate a user to use.

Abstract: A wireless electric power receiving device and a wireless electric power transmission system are disclosed. The wireless electric power receiving device is coupled to a wireless electric power transmitting device, and comprises a receiving coil, a power supply circuit and an alarm unit. When the receiving coil is coupled, a coupling voltage is generated and outputted. The power supply circuit comprises a first receiving terminal coupled to the receiving coil, and compares the voltage with a preset operation voltage range to generate and output a control signal when the voltage is beyond the range. The alarm unit is electrically coupled to the power supply circuit to receive the control signal from the power supply circuit and to output an alarm signal according to the control signal. The device can prevent a user from misusing a household appliance in case of a deficient voltage.

Abstract: A method and system for searching for information contained in a database of documents each includes an offline part and an online part. The offline part includes predicting, in a first computer process, semantic data for sentences of the documents contained in the database and storing this data in a database. The online part includes querying the database for information with a semantically-sensitive query, predicting, in a real time computer process, semantic data for the query, and determining, in a second computer process, a matching score against all the documents in the database, which incorporates the semantic data for the sentences and the query.

Abstract: A system and method for determining a similarity between a document and a query includes providing a frequently used dictionary and an infrequently used dictionary in storage memory. For each word or gram in the infrequently used dictionary, n words or grams are correlated from the frequently used dictionary based on a first score. Features for a vector of the infrequently used words or grams are replaced with features from a vector of the correlated words or grams from the frequently used dictionary when the features from a vector of the correlated words or grams meet a threshold value. A similarity score is determined between weight vectors of a query and one or more documents in a corpus by employing the features from the vector of the correlated words or grams that met the threshold value.

Abstract: A system and method for determining a similarity between a document and a query includes building a weight vector for each of a plurality of documents in a corpus of documents stored in memory and building a weight vector for a query input into a document retrieval system. A weight matrix is generated which distinguishes between relevant documents and lower ranked documents by comparing document/query tuples using a gradient step approach. A similarity score is determined between weight vectors of the query and documents in a corpus by determining a product of a document weight vector, a query weight vector and the weight matrix.

Abstract: Systems and methods are disclosed to perform preference learning on a set of documents includes receiving raw input features from the set of documents stored on a data storage device; generating polynomial combinations from the raw input features; generating one or more parameters; applying the parameters to one or more classifiers to generate outputs; determining a loss function and parameter gradients and updating parameters determining one or more sparse regularizing terms and updating the parameters; and expressing that one document is preferred over another in a search query and retrieving one or more documents responsive to the search query.

Abstract: Methods and systems for document classification include embedding n-grams from an input text in a latent space, embedding the input text in the latent space based on the embedded n-grams and weighting said n-grams according to spatial evidence of the respective n-grams in the input text, classifying the document along one or more axes, and adjusting weights used to weight the n-grams based on the output of the classifying step.

Abstract: A cell phone having distributed artificial intelligence services is provided. The cell phone includes a neural network for performing a first pass of object recognition on an image to identify objects of interest therein based on one or more criterion. The cell phone also includes a patch generator for deriving patches from the objects of interest. Each of the patches includes a portion of a respective one of the objects of interest. The cell phone additionally includes a transmitter for transmitting the patches to a server for further processing in place of an entirety of the image to reduce network traffic.

Abstract: A method for sentiment classification of a text document using high-order n-grams utilizes a multilevel embedding strategy to project n-grams into a low-dimensional latent semantic space where the projection parameters are trained in a supervised fashion together with the sentiment classification task. Using, for example, a deep convolutional neural network, the semantic embedding of n-grams, the bag-of-occurrence representation of text from n-grams, and the classification function from each review to the sentiment class are learned jointly in one unified discriminative framework.

Abstract: Systems and methods are disclosed to perform preference learning on a set of documents includes receiving raw input features from the set of documents stored on a data storage device; generating polynomial combinations from the raw input features; generating one or more parameters; applying the parameters to one or more classifiers to generate outputs; determining a loss function and parameter gradients and updating parameters determining one or more sparse regularizing terms and updating the parameters; and expressing that one document is preferred over another in a search query and retrieving one or more documents responsive to the search query.