Abstract: An “Interestingness Modeler” uses deep neural networks to learn deep semantic models (DSM) of “interestingness.” The DSM, consisting of two branches of deep neural networks or their convolutional versions, identifies and predicts target documents that would interest users reading source documents. The learned model observes, identifies, and detects naturally occurring signals of interestingness in click transitions between source and target documents derived from web browser logs. Interestingness is modeled with deep neural networks that map source-target document pairs to feature vectors in a latent space, trained on document transitions in view of a “context” and optional “focus” of source and target documents. Network parameters are learned to minimize distances between source documents and their corresponding “interesting” targets in that space.

Abstract: Disclosed herein are technologies directed to discovering semantic similarities between images and text, which can include performing image search using a textual query, performing text search using an image as a query, and/or generating captions for images using a caption generator. A semantic similarity framework can include a caption generator and can be based on a deep multimodal similar model. The deep multimodal similarity model can receive sentences and determine the relevancy of the sentences based on similarity of text vectors generated for one or more sentences to an image vector generated for an image. The text vectors and the image vector can be mapped in a semantic space, and their relevance can be determined based at least in part on the mapping. The sentence associated with the text vector determined to be the most relevant can be output as a caption for the image.

Abstract: In some examples, a computing device refines feature information of query text. The device repeatedly determines attention information based at least in part on feature information of the image and the feature information of the query text, and modifies the feature information of the query text based at least in part on the attention information. The device selects at least one of a predetermined plurality of outputs based at least in part on the refined feature information of the query text. In some examples, the device operates a convolutional computational model to determine feature information of the image. The device network computational models (NCMs) to determine feature information of the query and to determine attention information based at least in part on the feature information of the image and the feature information of the query. Examples include a microphone to detect audio corresponding to the query text.

Abstract: A processing unit can determine multiple representations associated with a statement, e.g., subject or predicate representations. In some examples, the representations can lack representation of semantics of the statement. The computing device can determine a computational model of the statement based at least in part on the representations. The computing device can receive a query, e.g., via a communications interface. The computing device can determine at least one query representation, e.g., a subject, predicate, or entity representation. The computing device can then operate the model using the query representation to provide a model output. The model output can represent a relationship between the query representations and information in the model. The computing device can, e.g., transmit an indication of the model output via the communications interface.

Abstract: A processing unit can operate a first recurrent computational model (RCM) to provide first state information and a predicted result value. The processing unit can operating a first network computational model (NCM) to provide respective expectation values of a plurality of actions based at least in part on the first state information. The processing unit can provide an indication of at least one of the plurality of actions, and receive a reference result value, e.g., via a communications interface. The processing unit can train the first RCM based at least in part on the predicted result value and the reference result value to provide a second RCM, and can train the first NCM based at least in part on the first state information and the at least one of the plurality of actions to provide a second NCM.

Abstract: The present invention provides a semiconductor test structure for MOSFET noise testing. The semiconductor test structure includes: a MOSFET device having a first conductivity type formed on a first well region of a semiconductor substrate; a metal shielding layer formed on the MOSFET device, the metal shielding layer completely covering the MOSFET device and extending beyond the circumference of the first well region; a deep well region having a second conductivity type formed in the semiconductor substrate close to the bottom surface of the first well region, the deep well region extending beyond the circumference of the first well region; wherein a vertical via is formed between the portion of the metal shielding layer extending beyond the first well region and the portion of the deep well region extending beyond the first well region to couple the metal shielding layer to the deep well region.

Abstract: A processing unit can successively operate layers of a multilayer computational graph (MCG) according to a forward computational order to determine a topic value associated with a document based at least in part on content values associated with the document. The processing unit can successively determine, according to a reverse computational order, layer-specific deviation values associated with the layers based at least in part on the topic value, the content values, and a characteristic value associated with the document. The processing unit can determine a model adjustment value based at least in part on the layer-specific deviation values. The processing unit can modify at least one parameter associated with the MCG based at least in part on the model adjustment value. The MCG can be operated to provide a result characteristic value associated with test content values of a test document.

Abstract: In various aspects, the disclosure relates to thermally conductive thermoplastic compositions comprising a polymer matrix, an impact modifier composition having a chemically reactive impact modifier, and, optionally, a chemically non-reactive impact modifier, and a thermally conductive filler. The disclosed thermally conductive thermoplastic compositions exhibit good thermal conductivity and improved impact and ductile properties.

Abstract: A computer-implemented technique is described herein for detecting actionable items in speech. In one manner of operation, the technique entails: receiving utterance information that expresses at least one utterance made by one participant of a conversation to at least one other participant of the conversation; converting the utterance information into recognized speech information; using a machine-trained model to recognize at least one actionable item associated with the recognized speech information; and performing at least one computer-implemented action associated the actionable item(s). The machine-trained model may correspond to a deep-structured convolutional neural network. In some implementations, the technique produces the machine-trained model using a source environment corpus that is not optimally suited for a target environment in which the model is intended to be applied.

Abstract: Methods, systems, and computer-readable media for query simplification are provided. A search engine executed by a server receives a query. In response, the search engine determines whether the query is a long or hard query. For long or hard queries, the search engine drops one or more terms based on search engine logs. The search engine may utilize statistical models like machine translation, condition random fields, or max entropy, to identify the terms that should be dropped. The search engine obtains search results for the simplified query and transmits the results to a user that provided the query.

Abstract: Disclosed herein are technologies directed to discovering semantic similarities between images and text, which can include performing image search using a textual query, performing text search using an image as a query, and/or generating captions for images using a caption generator. A semantic similarity framework can include a caption generator and can be based on a deep multimodal similar model. The deep multimodal similarity model can receive sentences and determine the relevancy of the sentences based on similarity of text vectors generated for one or more sentences to an image vector generated for an image. The text vectors and the image vector can be mapped in a semantic space, and their relevance can be determined based at least in part on the mapping. The sentence associated with the text vector determined to be the most relevant can be output as a caption for the image.

Abstract: Systems, methods, and computer-readable media for providing semantically-relevant discovery of solutions are described herein. In some examples, a computing device can receive an input, such as a query. The computing device can process each word of the input sequentially to determine a semantic representation of the input. Techniques and technologies described herein determine a response to the input, such as an answer, based on the semantic representation of the input matching a semantic representation of the response. An output including one or more relevant responses to the request can then be provided to the requestor. Example techniques described herein can apply machine learning to train a model with click-through data to provide semantically-relevant discovery of solutions. Example techniques described herein can apply recurrent neural networks (RNN) and/or long short term memory (LSTM) cells in the machine learning model.

Abstract: A system may comprise one or more processors and memory storing instructions that, when executed by one or more processors, configure one or more processors to perform a number of operations or tasks, such as receiving a query or a document, and mapping the query or the document into a lower dimensional representation by performing at least one operational layer that shares at least two disparate tasks.

Abstract: A deep learning network is trained to automatically analyze enterprise data. Raw data from one or more global data sources is received, and a specific training dataset that includes data exemplary of the enterprise data is also received. The raw data from the global data sources is used to pre-train the deep learning network to predict the results of a specific enterprise outcome scenario. The specific training dataset is then used to further train the deep learning network to predict the results of a specific enterprise outcome scenario. Alternately, the raw data from the global data sources may be automatically mined to identify semantic relationships there-within, and the identified semantic relationships may be used to pre-train the deep learning network to predict the results of a specific enterprise outcome scenario.

Abstract: A high-voltage device simulation model and a modeling method thereof are provided. The simulation model comprises: a core transistor (101), a drain terminal resistor (102) and a source terminal resistor (103), wherein a first terminal of the drain terminal resistor (102) is electrically connected to a drain (d1) of the core transistor (101) and a second terminal of the drain terminal resistor (102) serves as the drain of the high voltage device; a first terminal of the source terminal resistor (103) is electrically connected to a source (s1) of the core transistor (101) and a second terminal of the source terminal resistor (103) serves as the source of the high voltage device. The relations of the resistance value of the drain terminal resistor (102) are as follows: RD=(RD0/W)*(1+CRD*VDERDD+1/(1+PRWDD*VDERDD))*TFAC_RD, and TFAC_RD=(1+TCRD1*(TEMP?25)+TCRD2*(TEMP?25)*(TEMP?25)).

Abstract: A search engine is described herein for providing search results based on a context in which a query has been submitted, as expressed by context information. The search engine operates by ranking a plurality of documents based on a consideration of the query, and based, in part, on a context concept vector and a plurality of document concept vectors, both generated using a deep learning model (such as a deep neural network). The context concept vector is formed by a projection of the context information into a semantic space using the deep learning model. Each document concept vector is formed by a projection of document information, associated with a particular document, into the same semantic space using the deep learning model. The ranking operates by favoring documents that are relevant to the context within the semantic space, and disfavoring documents that are not relevant to the context.

Abstract: A processing unit can acquire datasets from respective data sources, each having a respective unique data domain. The processing unit can determine values of a plurality of features based on the plurality of datasets. The processing unit can modify input-specific parameters or history parameters of a computational model based on the values of the features. In some examples, the processing unit can determine an estimated value of a target feature based at least in part on the modified computational model and values of one or more reference features. In some examples, the computational model can include neural networks for several input sets. An output layer of at least one of the neural networks can be connected to the respective hidden layer(s) of one or more other(s) of the neural networks. In some examples, the neural networks can be operated to provide transformed feature value(s) for respective times.

Abstract: A wavy-shaped electric straight comb, which includes a comb part and a handle. The comb part has a first comb and a second comb, and the first comb has a plurality of first comb teeth, and the second comb has a plurality of second comb teeth, a plurality of through holes, each formed between two adjacent second comb teeth, which the plurality of first comb teeth of the first comb respectively drills through the plurality of through holes of the second comb, and each first comb teeth is disposed between two corresponding adjacent comb teeth, for assembling the first comb and the second comb together, and each of the first comb teeth and the second comb teeth defines a wavy-shaped cross-section, and two adjacent first and second comb teeth keep an interval from 0.25 mm to 1.5 mm and define a wavy-shaped hair accommodating space.

Abstract: A deep structured semantic module (DSSM) is described herein which uses a model that is discriminatively trained based on click-through data, e.g., such that a conditional likelihood of clicked documents, given respective queries, is maximized, and a condition likelihood of non-clicked documents, given the queries, is reduced. In operation, after training is complete, the DSSM maps an input item into an output item expressed in a semantic space, using the trained model. To facilitate training and runtime operation, a dimensionality-reduction module (DRM) can reduce the dimensionality of the input item that is fed to the DSSM. A search engine may use the above-summarized functionality to convert a query and a plurality of documents into the common semantic space, and then determine the similarity between the query and documents in the semantic space. The search engine may then rank the documents based, at least in part, on the similarity measures.

Abstract: Systems, methods, and computer media for identifying related strings for search query rewriting are provided. Session data for a user search query session in an accessed click log data is identified. It is determined whether a first additional search query in the session data is related to a first user search query based on at least one of: dwell time; a number of search result links clicked on; and similarity between web page titles or uniform resource locators (URLs). When related, the first additional search query is incorporated into a list of strings related to the first user search query. One or more supplemental strings that are related to the first user search query are also identified. The identified supplemental strings are also included in the list of strings related to the first user search query.