Abstract: Described is an inference circuit for pattern recognition for use within convolutional neural nets for online learning using K-means clustering. The inference circuit includes a set of templates, each template having a template data memory. The inference circuit also include at least one match element, the match element being operable for receiving an input data pattern and determining a degree of match between the input data pattern and a template. A best match logic circuit is included for selecting a template in the set of templates that best matches the input data pattern, said template being a best match template. Finally, an updated is included for probabilistically modifying the template data memories based on the best match template.

Abstract: A weak binary classifier configured to receive an input signal for classification and generate a classification output is disclosed. The weak binary classifier includes a plurality of weighting amplifier stages, each weighting amplifier stage being configured to receive the input signal for classification and a weighting input derived from a classifier model and generate a weighted input signal, the plurality of weighting amplifier stages being configured to generate a plurality of positive weighted input signals coupled to a positive summing node and a plurality of negative weighted input signals coupled to a negative summing node. The weak binary classifier also includes a comparator having a non-inverting input coupled to the positive summing node and an inverting input coupled to the negative summing node and being configured to generate a weak classification output based on the plurality of weighted input signals.

Abstract: A utility management device, comprising an input for receiving a utility consumption signal for a premises, an output for outputting utility management information, and a processor configured to monitor the input utility consumption signal for a change in magnitude. If a change is detected, the processor is configured to identify an appliance event corresponding to the change, obtain information relating to the projected utility consumption of the appliance for an upcoming time period, update a projected utility consumption of the premises based on the obtained information, determine whether any projected stored and/or generated utility amount at the premises is sufficient for the projected utility consumption of the premises, and, if not sufficient, cause the device to output a request to receive a utility amount from one or more other premises connected to the premises via a communication network.

Abstract: To make predictions about racing, a point to pay attention to in pre-race movements of each racer can be presented. To this end, for racers entered in a race to be processed, a plurality of captured pre-race movement images of pre-race movements made by the racers before a race are retrieved. By using the retrieved pre-race movement images and racing result information corresponding to each pre-race movement image, an attention point to be paid attention to while each racer is making pre-race movements are identified. Presentation information for presenting information about the identified attention point is then generated and controlled to be presented to a user on an external terminal.

Abstract: Audio sensors collaborate for geo-location and tracking of health conditions for multiple users. Different users can be independently geo-located and tracked within the AI environment. Location is determined from two or more AI clients of known locations that detect an event such as a human voice command to connect a call with a specific user. Responsive to classification of a health event of concern, in view of the estimated location, a command for an AI action, such as contacting a hospital server or adapting to monitor a suspected health condition, is received for a response to the health event at the AI clients that detected the health event, or others.

Abstract: A three-dimensional integration of synapse circuitry is formed. One or more neuron layers each comprises a plurality of computing elements, and one or more synapse layers each comprising an array of memory elements are formed on top of the one or more neuron layers. A plurality of staggered through-silicon vias (TSVs) connect the one or more neuron layers to the one or more synapse layers and operate as communication links between one or more computing elements in the one or more neuron layers and one or more memory elements in the one or more synapse layers.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining a global model for a particular activity, the global model derived based on input data representing multiple observations associated with the particular activity performed by a collection of users; determining, using the global model, expected data representing an expected observation associated with the particular activity performed by a particular user; receiving, by a computing device operated by the particular user, particular data representing an actual observation associated with the particular activity performed by the particular user; determining, by the computing device and using (i) the expected data and (ii) the particular data, residual data of the particular user; and deriving a local model of the particular user based on the residual data.

Abstract: Generally discussed herein are devices, systems, and methods for encoding input-output examples. A method of generating a program using an encoding of input-output examples, may include processing an input example of the input-output examples, using a first long short term memory (LSTM) neural network, one character at a time to produce an input feature vector, processing an output example associated with the input example in the input-output examples, using the LSTM neural network, one character at a time to produce an output feature vector, determining (a) a cross-correlation between the input feature vector and the output feature vector or (b) previously computed feature vectors for a different input-output example that are sufficiently close to the input feature vector and the output feature vector, respectively, and using the determined cross-correlation or previously computed vector, generating a program consistent with the input example and the output example.

Abstract: According to an exemplary embodiment of the present disclosure, disclosed is a computer program stored in a computer readable storage medium. When the computer program is executed in one or more processors, the computer program performs the following method for anomaly detection of data using a network function, and the method includes: generating an anomaly detection model including a plurality of anomaly detection sub models including a trained network function using a plurality of training data sub sets included in the training data set; calculating input data using at least one of the plurality of generated anomaly detection sub models; and determining whether there is an anomaly in the input data based on output data for input data of at least one of the plurality of generated anomaly detection sub models and the input data.

Abstract: Techniques are described for identifying an input training dataset stored within an underlying data platform; and transmitting instructions to the data platform, the instructions being executable by the data platform to train a predictive model based on the input training dataset by delegating one or more data processing operations to a plurality of nodes across the data platform.

Abstract: A method is provided for the enabling of machine functions on a spinning-mill machine comprising multiple components. The method includes transfer of machine-specific data to an enabling device that is physically remote from the spinning-mill machine; evaluation of the machine-specific data through the enabling device; selection of enabling data through the enabling device depending on the machine-specific data; transfer of the enabling data to the spinning-mill machine; and enabling of specific machine functions depending on the enabling data.

Abstract: Architecture introduces a new pattern operator referred to as called an augmented transition network (ATN), which is a streaming adaptation of non-reentrant, fixed-state ATNs for dynamic patterns. Additional user-defined information is associated with automaton states and is accessible to transitions during execution. ATNs are created that directly model complex pattern continuous queries with arbitrary cycles in a transition graph. The architecture can express the desire to ignore some events during pattern detection, and can also detect the absence of data as part of a pattern. The architecture facilitates efficient support for negation, ignorable events, and state cleanup based on predicate punctuations.

Abstract: A computer-implemented method and system create a three-dimensional (3D) model of a personalized object that represents of a real-world physical product. The 3D model contains one or more symbol parts, where each of the symbol parts is a computer representation of a symbol and a 3D font determines the shape of each of the symbol parts. A user interface is provided to enable a user to specify the symbol parts to personalize the real-world physical product. A transformation operation is performed, which transforms the 3D model in any one of the six degrees of freedom and enables a user to visualize in three dimensions on a computer screen a representation of the physical product prior to purchase.

Abstract: A device includes a storage unit and a processing unit. The processing unit includes a processor and is coupled to the storage unit. The processing unit operates a big operating system (BOS) and a little operating system (LOS) and can dynamically switch between the BOS and the LOS according to the system loading status of the device, wherein power consumption and resource requirements of the BOS are different than those of the LOS.

Abstract: Methods, systems and apparatuses, including computer programs encoded on computer storage media, are provided for learning or optimizing an indirect encoding of a mapping from digitally-encoded input arrays to digitally-encoded output arrays, with numerous technical advantages in terms of efficiency and effectiveness.

Abstract: A neural network unit includes a register programmable with a control value, a plurality of neural processing units (NPU), and a plurality of activation function units (AFU). Each NPU includes an arithmetic logic unit (ALU) that performs arithmetic and logical operations on a sequence of operands to generate a sequence of results and an accumulator into which the ALU accumulates the sequence of results as an accumulated value. Each AFU includes a first module that performs a first function on the accumulated value to generate a first output, a second module that performs a second function on the accumulated value to generate a second output, the first function is distinct from the second function, and a multiplexer that receives the first and second outputs and selects one of the two outputs based on the control value programmed into the register.

Abstract: An answer to a question may selected from answers from a set of answering pipelines. Question answer data can be generated for a question, using a first answering pipeline. Another set of question answer data can be generated for the second question, using the second answering pipeline. The question answer data can include answers and confidence values for each answer. Using a weighting formula and a blending profile for the first answering pipeline, a vote weight can be determined for an answer with the highest confidence value. The same weighting formula and a second blending profile may be used to determine a vote weight for another answer with the highest confidence value. An answer to the question may be selected from the answers, based on the overall highest vote weight.

Abstract: Disclosed are systems and methods that implement efficient engines for computation-intensive tasks such as neural network deployment. Various embodiments of the invention provide for high-throughput batching that increases throughput of streaming data in high-traffic applications, such as real-time speech transcription. In embodiments, throughput is increased by dynamically assembling into batches and processing together user requests that randomly arrive at unknown timing such that not all the data is present at once at the time of batching. Some embodiments allow for performing steaming classification using pre-processing. The gains in performance allow for more efficient use of a compute engine and drastically reduce the cost of deploying large neural networks at scale, while meeting strict application requirements and adding relatively little computational latency so as to maintain a satisfactory application experience.

Abstract: Various systems and methods for counting people. For example, one method involves receiving input data at an analytics system that includes a neural network. The input data includes a representation of an environment, including representations of several people. The method also includes identifying the representations of the people in the representation of the environment. The method also includes updating an output value that indicates the number of people identified as being present in the environment.

Abstract: Described is a neuromorphic system implemented in hardware that implements neuron membrane potential update based on the leaky integrate and fire (LIF) model. The system further models synapse weights update based on the spike time-dependent plasticity (STDP) model. The system includes an artificial neural network in which the update scheme of neuron membrane potential and synapse weight are effectively defined and implemented.