Login| Sign Up| Help| Contact|

Patent Searching and Data


Matches 1 - 50 out of 12,059

Document Document Title
WO/2019/049686A1
A combining weight coefficient used in neural network computation is stored in a memory array (20), a word line (22) corresponding to the input data of a neural network is driven by a word line drive circuit (24), and a bit line to which...  
WO/2019/049741A1
A neural network arithmetic circuit for outputting output data (y) in accordance with the results of a multiply-add operation performed on input data (x0-xn) and connection weight coefficients (w0-wn), wherein the neural network arithmet...  
WO/2019/048982A1
The purpose of the present invention is to provide a computation device and electronic equipment that consume little power. The purpose of the present invention is to provide a computation device and electronic equipment capable of high-...  
WO/2019/049127A1
An efficient technique of machine learning is provided for training a plurality of convolutional neural networks (CNNs) with increased speed and accuracy using a genetic evolutionary model. A plurality of artificial chromosomes may be st...  
WO/2019/049842A1
Provided is a neural network computation circuit capable of outputting output data according to the result of a multiply-accumulate operation performed on input data and connection weight coefficients, said circuit comprising a computati...  
WO/2019/048979A1
Provided is electronic equipment having a semiconductor device capable of intermittent operation. The electronic equipment has a semiconductor device, and the semiconductor device has a current mirror circuit, a bias circuit and first th...  
WO/2019/049113A1
Many computer aided design (CAD) models include components that are supplied via third party vendors, also know as suppliers. These suppliers create CAD models of their components, place them in a library organized by logical categories,...  
WO/2019/051067A1
Systems, methods and computer program products for cannabis analysis, such as a system that has a cannabis analysis data server and a plurality of mobile cannabis analysis devices that are communicatively coupled to a network. The mobile...  
WO/2019/049654A1
A neural network computation circuit comprising an in-area word line multiple selection circuit for logically segmenting a plurality of word lines of a memory array (10) into a plurality of word line areas and making a given word line se...  
WO/2019/045758A1
A method is described for training a predictive model which increases the interpretability and trustworthiness of the model for end-users. The model is trained from data having multitude of features. Each feature is associated with a rea...  
WO/2019/040927A1
A method, executed at least in part by a computer, acquires three- dimensional data from scans of maxillofacial and dental anatomy of a patient and computes cephalometric values from the acquired three-dimensional data. The method proces...  
WO/2019/038423A1
A decoding device includes storage to store image data including grayscale values of pixels in multiple captured images, and a processor including multiple SIMD components and at least one component. For each captured image at least one ...  
WO/2019/021024A1
A method of treating lower limb spasticity in a subject, particularly one which is 18 years of age or under, comprising administering to the subject an effective amount of botulinum neurotoxin. A composition for use in treating lower lim...  
WO/2019/022741A1
A method of operating switched capacitor filter integration circuits by pre-charging a final filter capacitor thereof with the final full voltage gain value during a first subframe to obtain an enhanced signal to noise ratio without chan...  
WO/2019/012369A1
The present invention reduces the offset component from transistor multiplication. This imaging device comprises a pixel region, a first circuit, a second circuit, a third circuit, and a fourth circuit. The pixel region has a plurality o...  
WO/2019/008951A1
Provided is a convolutional neural network (20) including a first convolutional layer (22, 24), a pooling layer (28, 29), and a second convolutional layer (23, 25), and comprising: a crossbar circuit (44) provided with a plurality of inp...  
WO/2019/003046A1
Provided are a portable information terminal with a novel configuration, and a problem solving system. The portable information terminal is provided with an input computation unit, a signal transmission/reception unit, and an output comp...  
WO/2018/235448A1
Provided is a method for adjusting the output level of neurons in a multilayer neural network (20) comprising: a memristor (53) being a variable-resistance memory that applies weighting, in order to perform signal transmission between hi...  
WO/2018/235449A1
Provided is a training method for an artificial neural network circuit (40) that comprises a crossbar circuit (44) having a plurality of input bars (50), a plurality of output bars (51), and a memristor (53) and wherein each memristor ha...  
WO/2018/234919A1
Provided is a semiconductor device capable of efficiently performing image recognition using a neural network. The semiconductor device comprises: a shift register group; a D/A converter; and a multiply-accumulate circuit. The multiply-a...  
WO/2018/220957A1
A neural network (20) is provided with a plurality of convolution layers (21-27) and a merging layer (63). One convolution layer has a crossbar circuit (44) that has a plurality of input bars (50), a plurality of output bars (51, 52), an...  
WO/2018/222909A1
Systems and methods of automated and efficient camera selection are provided as useful tools for first responders and other contexts.  
WO/2018/217786A1
Methods and systems are described for obtaining, at an input stage of a sampler, a continuous-time analog differential voltage, and responsively generating an integrated analog differential voltage by discharging a pair of pre-charged ou...  
WO/2018/213109A1
The present invention is directed towards objective methods of manufacture of pharmaceuticals that eliminate or greatly reduce the use of the subjective, empirical methods of the prior art. In a preferred embodiment, the methods utilize ...  
WO/2018/207050A1
Provided is a novel sum-of-products operation device which is highly reliable and easy to use. Further provided is a novel neuron circuit which is highly reliable and easy to use. A sum-of-products operation circuit comprises a sum-of-pr...  
WO/2018/204227A1
Protective IEDs in an electrical power system, such as distributed controllers, may periodically or in real-time communicate updated protection settings to a wide-area controller, such as a coordination controller, that defines and/or im...  
WO/2018/204936A1
Work at each Work Center in a production system is authorized by a demand-pull system. The demand-pull system can be based on the time for the oldest unauthorized work order in upstream adjacent WCs to get to the next WC and whether that...  
WO/2018/204316A1
The systems, methods, and apparatuses described herein provide integrated weather forecast products designed to assist operations managers with operational decision-making related to a designated event or set of events. The present discl...  
WO/2018/194598A1
A current value of at least one operational attribute of a current treatment stage of multiple treatment stages of a wellbore treatment operation of a current well in real time is determined. A determination is made of whether a statisti...  
WO/2018/189619A1
Provided is a novel neuron connection for neural networks. A perceptron possessed by a neural network comprises a plurality of neurons, each neuron comprises a synapse circuit and an activation function circuit, and each synapse circuit ...  
WO/2018/186390A1
The present invention provides a semiconductor device comprising: an input unit 1 to which a voltage is applied; a current output unit 3 that outputs a high-level current or a low-level current in accordance with the voltage applied to t...  
WO/2018/186820A1
In example implementations, a method for starting a companion application on a mobile endpoint device and an apparatus for performing the same is provided. The method is performed by a processor of the mobile endpoint device. The method ...  
WO/2018/184025A1
This invention relates to boring systems. Previously, drilling contractors were forced unnecessarily to suspend operations and pull their well control equipment back to the surface for repairs because they could not articulate a compelli...  
WO/2018/173472A1
The present invention: comprises a storage unit that uses memristors as storage elements; and uses a ramp function as an activation function. A differential amplifier circuit: performs a differential computation on a pair of outputs from...  
WO/2018/173473A1
The present invention uses memristors that are variable resistance elements as storage elements and comprises a storage unit in which the storage elements are joined together in a grid pattern. I/V conversion amplifier circuits convert c...  
WO/2018/168293A1
A neural network circuit is provided with which it is possible to significantly reduce the area occupied by the connection unit of an FC-type neural network circuit. An analog-type neural network circuit SS constituting a learning device...  
WO/2018/159073A1
According to an aspect of the present disclosure, provided is a storage unit which is formed by coupling memristors, which are storage elements, in a grid shape. A control unit controls a voltage applying unit in order to perform a write...  
WO/2018/156282A1
An optimal sample size for experiments targeting units having specific static criteria is determined, based on one or more iterations of a performed experiment. The sample size to use for subsequent experiments targeting units having the...  
WO/2018/140704A1
Systems, methods, and computer program products can be used for visualizing the behavior of flow of two or more fluid phases, wherein a fluid phase behavior is represented in a visualization. One of the methods includes determining an oc...  
WO/2018/132786A1
A system and method for predicting well production at various stages in the life cycle of the well utilizes data received from a plurality of databases via one or more database interfaces to generate various attributes that can be used t...  
WO/2018/125613A1
Directional drilling is an extremely important area of technology for the extraction of oil and gas from earthen formations. The technology of the present application relates to improved non-stabilizer guidance positioning members for di...  
WO/2018/125881A1
Systems, apparatuses, and methods are provided herein for stocking a store. A system for stocking a store comprises a plurality of mobile modular displays, a store inventory database, and a control circuit. The control circuit configured...  
WO/2018/125899A1
Systems, apparatuses, and methods are provided herein for use with mobile modular displays. An apparatus for product display comprises a housing of a mobile modular display, a wheel system coupled to the housing and configured to travel ...  
WO/2018/118335A1
A system and method for reducing the complexity of the reservoir simulation process is described. In more detail, an add-in for spreadsheet software program has been developed allowing a user to input minimal amount of information for a ...  
WO/2018/117502A1
The present invention provides a hybrid wave computer for calculating an input original signal into frequency information, the hybrid wave computer comprising: an input module which delivers, in the form of acoustic waves, an original si...  
WO/2018/117322A1
The present invention relates to an integrator using a single gain buffer and including: a positive differential switched-capacitor which adds a positive input signal to a value stored in a previous phase, and cumulates and stores the ad...  
WO/2018/111913A1
The present invention provides methods of predicting and monitoring treatment with a gastrointestinal implant (e.g., a gastrointestinal sleeve), including efficacy and complications associated therewith (e.g., complications attributed to...  
WO/2018/106748A1
A method includes representing oilfield operational plan information as pixels where the pixels include pixels that correspond to a plurality of different state variables associated with oilfield operations; training a deep neural networ...  
WO/2018/102565A1
A computer-implemented method for finding a transition state for a chemical reaction includes obtaining a graphical representation of one or more reactants of the chemical reaction via a graphical user interface (GUI); (ii) obtaining a g...  
WO/2018/102271A1
Methods for using shut-in pressures to determine uncertainties in a hydraulic fracturing process in a shale reservoir are described. Data commonly collected during multistage fracturing is used to calculate propped fracture height and in...  

Matches 1 - 50 out of 12,059