Abstract: A processing unit can determine a first feature value corresponding to a session by operating a first network computational model (NCM) based part on information of the session. The processing unit can determine respective second feature values corresponding to individual actions of a plurality of actions by operating a second NCM. The second NCM can use a common set of parameters in determining the second feature values. The processing unit can determine respective expectation values of some of the actions of the plurality of actions based on the first feature value and the respective second feature values. The processing unit can select a first action of the plurality of actions based on at least one of the expectation values. In some examples, the processing unit can operate an NCM to determine expectation values based on information of a session and information of respective actions.

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: 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: 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: 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: 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 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 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: Embodiments described herein may fully integrate personal computing and health care into a wearable waistband having a length sensor, a pressure sensor, and a motion sensor; or into a wearable “mesh” having an array of sound sensors, which will create convenient and seamless access to a personal computer and biofeedback of the wearer. Such biofeedback from the waistband may include determining respiration rate, waist length, food quantity of a meal, sitting or sleep time, and frequency of visits to the bathroom. Such biofeedback from the mesh or array may include determining whether there is or has been damage or other issues of the heart, lungs, bones, joints, jaw, throat, arteries, digestive tract, and the like. Such biofeedback may also detect whether whether a person has an allergic reaction at a location, is drinking (and what volume of fluid), is walking, is jogging or is running.

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: Functionality is described herein for transforming first and second symbolic linguistic items into respective first and second continuous-valued concept vectors, using a deep learning model, such as a convolutional latent semantic model. The model is designed to capture both the local and global linguistic contexts of the linguistic items. The functionality then compares the first concept vector with the second concept vector to produce a similarity measure. More specifically, the similarity measure expresses the closeness between the first and second linguistic items in a high-level semantic space. In one case, the first linguistic item corresponds to a query, and the second linguistic item may correspond to a phrase, or a document, or a keyword, or an ad, etc. In one implementation, the convolutional latent semantic model is produced in a training phase based on click-through data.

Abstract: Ultra-short pulsed laser radiation is applied to a patient's eye to create a row of bubbles oriented perpendicular to the axis of vision. The row of bubbles leads to a region of the eye to be ablated. In a second step, a femtosecond laser beam guided through the row of bubbles converts it to a channel perpendicular to the axis of vision. In a third step, a femtosecond laser beam is guided through the channel to ablate a portion of the eye. Using a femtosecond laser with intensity in the range of 1011-1015 W/cm2 for the second and third steps facilitates multi-photon ablation that is practically devoid of eye tissue heating. Creating bubbles in the first step increases the speed of channel creation and channel diameter uniformity, thereby increasing the precision of the subsequent multi-photon ablation.

Abstract: A method is disclosed herein that includes an act of causing a processor to access a deep-structured, layered or hierarchical model, called a deep convex network, retained in a computer-readable medium, wherein the deep-structured model comprises a plurality of layers with weights assigned thereto. This layered model can produce the output serving as the scores to combine with transition probabilities between states in a hidden Markov model and language model scores to form a full speech recognizer. Batch-based, convex optimization is performed to learn a portion of the deep convex network's weights, rendering it appropriate for parallel computation to accomplish the training. The method can further include the act of jointly substantially optimizing the weights, the transition probabilities, and the language model scores of the deep-structured model using the optimization criterion based on a sequence rather than a set of unrelated frames.

Abstract: Ultra-short pulsed laser radiation is applied to a patient's eye to create a row of bubbles oriented perpendicular to the axis of vision. The row of bubbles leads to a region of the eye to be ablated. In a second step, a femtosecond laser beam guided through the row of bubbles converts it to a channel perpendicular to the axis of vision. In a third step, a femtosecond laser beam is guided through the channel to ablate a portion of the eye. Using a femtosecond laser with intensity in the range of 1011-1015 W/cm2 for the second and third steps facilitates multi-photon ablation that is practically devoid of eye tissue heating. Creating bubbles in the first step increases the speed of channel creation and channel diameter uniformity, thereby increasing the precision of the subsequent multi-photon ablation.

Abstract: A light emitting diode (LED) driver includes a first and second switches and control logic. The first switch is configured to switch on and off to regulate a voltage level at an output voltage node. The voltage level at the output voltage node is to power multiple LEDs. The second switch is configured to switch on and off to vary brightness of the LEDs. Based on an external signal, the control logic is configured to control first and second control signals to switch on and off the first and second switches, respectively. Based on an active time portion of the external signal, the control logic concurrently determines an active time portion of the second control signal and a number of switching cycles of the first control signal to switch on and off the first switch.

Abstract: A deep tensor neural network (DTNN) is described herein, wherein the DTNN is suitable for employment in a computer-implemented recognition/classification system. Hidden layers in the DTNN comprise at least one projection layer, which includes a first subspace of hidden units and a second subspace of hidden units. The first subspace of hidden units receives a first nonlinear projection of input data to a projection layer and generates the first set of output data based at least in part thereon, and the second subspace of hidden units receives a second nonlinear projection of the input data to the projection layer and generates the second set of output data based at least in part thereon. A tensor layer, which can converted into a conventional layer of a DNN, generates the third set of output data based upon the first set of output data and the second set of output data.

Abstract: Discriminative pretraining technique embodiments are presented that pretrain the hidden layers of a Deep Neural Network (DNN). In general, a one-hidden-layer neural network is trained first using labels discriminatively with error back-propagation (BP). Then, after discarding an output layer in the previous one-hidden-layer neural network, another randomly initialized hidden layer is added on top of the previously trained hidden layer along with a new output layer that represents the targets for classification or recognition. The resulting multiple-hidden-layer DNN is then discriminatively trained using the same strategy, and so on until the desired number of hidden layers is reached. This produces a pretrained DNN. The discriminative pretraining technique embodiments have the advantage of bringing the DNN layer weights close to a good local optimum, while still leaving them in a range with a high gradient so that they can be fine-tuned effectively.