Abstract: Disclosed are an apparatus and a method for LDPC encoding suitable for highly reliable and low latency communication. The disclosed apparatus comprises: a second inner encoding module for outputting parity bits by means of single parity calculations and accumulation device calculations using bit strings outputted from a first inner encoding module; and the first inner encoding module for outputting a part of the parity bits by means of single parity check calculations for the bits output from a second outer module, and for outputting rest of the parity bit strings by means of single parity check calculations and accumulation device calculations, with a part of the parity bits output by the second inner encoding module as an additional input.

Abstract: A computer-implemented method, computer program product, and computer processing system are provided for generating inferences from a forest of predefined problem determination trees using a processor-based conversation platform. The method includes selecting a tree from among the forest of predefined problem determination trees, responsive to user utterances uttered during an inference generating session. The method further includes navigating the tree to allocate a relevant tree node to generate a problem diagnosis question or a problem resolution action by understanding the user utterances among common interaction patterns in problem diagnosis and problem resolution dialogs. The method also includes providing speech for uttering the problem diagnosis question or the problem resolution action to a user.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine learning tasks. One method includes receiving (i) a model input, and (ii) data identifying a first machine learning task to be performed on the model input to generate a first type of model output for the model input; augmenting the model input with an identifier for the first machine learning task to generate an augmented model input; and processing the augmented model input using a machine learning model. An exemplary system applying implicit bridging for machine learning tasks, as described in this specification, trains a machine learning model to perform certain types of machine learning tasks without requiring explicit training data for the certain types of machine learning tasks to be used during training.

Abstract: Methods and systems for receiving a request to implement a neural network comprising an average pooling layer on a hardware circuit, and in response, generating instructions that when executed by the hardware circuit, cause the hardware circuit to, during processing of a network input by the neural network, generate a layer output tensor that is equivalent to an output of the average pooling neural network layer by performing a convolution of an input tensor to the average pooling neural network layer and a kernel with a size equal to a window of the average pooling neural network layer and composed of elements that are each an identity matrix to generate a first tensor, and performing operations to cause each element of the first tensor to be divided by a number of elements in the window of the average pooling neural network layer to generate an initial output tensor.

Abstract: Embodiments are directed to a driver circuit including a first amplifier having a voltage follower configured to control a first node to maintain a voltage of the first node at a constant value. By maintaining the first node voltage, the first amplifier having the voltage follower is further configured to have a first amplifier output current into the first node at a value without the effect of the voltage fluctuation. The driver circuit further includes a second amplifier configured to control a second node, wherein the second amplifier is in a current mirror configuration with respect to the first amplifier such that a second amplifier current output is a highly precise mirror of the first amplifier current output.

Abstract: Technologies for memory management of a neural network include a compute device to read a memory of the compute device to access connectivity data associated with a neuron of the neural network, determine a memory address at which weights corresponding with the one or more network connections are stored, and access the corresponding weights from a memory location corresponding with the memory address. The connectivity data is indicative of one or more network connections from the neuron.

Abstract: Described is a system for proactive and reactive cognitive control using a neural module. The system calculates, for each hypothesis of a set of hypotheses, a probability that an event will occur. The neural module comprises a plurality of neurons and includes the PC module, a prefrontal cortex (PFC) module, an anterior cingulate cortex (ACC) module, a locus coeruleus (LC) module, and a basal forebrain (BF) module. The set of hypotheses are related to tasks to be performed by a plurality of groups, each group having a corresponding hypothesis. For each probability, the system calculates a conflict value across all hypotheses with the ACC module, compares each conflict value to a predetermined threshold using the BF and LC modules. A determination is made whether to directly output the calculated probability or perform an additional probability calculation and output an updated probability.

Abstract: A method receives user behavior information at a first system. The user behavior information is determined by user interaction with a first list sent to the user by a first network on a video delivery service. A first state is generated using the received user behavior information and prior user behavior information by the user from cells that store the prior user behavior. The method inputs the first state into a second network with the first recommendation list to generate a value that evaluates a performance of recommending the first recommendation list. An update to parameters is generated for the first network and provided to the first network. The first network generates a second state from the received user behavior information and prior user behavior information derived from cells that store the prior user behavior and outputs a second recommendation list using the second state and updated parameters.

Abstract: Aspects disclosed in the detailed description include memory compression in a deep neural network (DNN). To support a DNN application, a fully connected weight matrix associated with a hidden layer(s) of the DNN is divided into a plurality of weight blocks to generate a weight block matrix with a first number of rows and a second number of columns. A selected number of weight blocks are randomly designated as active weight blocks in each of the first number of rows and updated exclusively during DNN training. The weight block matrix is compressed to generate a sparsified weight block matrix including exclusively active weight blocks. The second number of columns is compressed to reduce memory footprint and computation power, while the first number of rows is retained to maintain accuracy of the DNN, thus providing the DNN in an efficient hardware implementation without sacrificing accuracy of the DNN application.

Abstract: Systems and Methods for multi-modal or multimedia image retrieval are provided. Automatic image annotation is achieved based on a probabilistic semantic model in which visual features and textual words are connected via a hidden layer comprising the semantic concepts to be discovered, to explicitly exploit the synergy between the two modalities. The association of visual features and textual words is determined in a Bayesian framework to provide confidence of the association. A hidden concept layer which connects the visual feature(s) and the words is discovered by fitting a generative model to the training image and annotation words. An Expectation-Maximization (EM) based iterative learning procedure determines the conditional probabilities of the visual features and the textual words given a hidden concept class. Based on the discovered hidden concept layer and the corresponding conditional probabilities, the image annotation and the text-to-image retrieval are performed using the Bayesian framework.

Abstract: By way of example, the technology disclosed by this document is capable of receiving signal data from one or more sensors; inputting the signal data into an input layer of a deep neural network (DNN), the DNN including one or more layers; generating, using the one or more layers of the DNN, one or more spatial representations of the signal data; generating, using one or more hierarchical temporal memories (HTMs) respectively associated with the one or more layers of the DNNs, one or more temporal predictions by the DNN based on the one or more spatial representations; and generating an anticipation of a future outcome by recognizing a temporal pattern based on the one or more temporal predictions.

Abstract: A machine learning device capable of preventing spoofing of an operator to secure safety during an operation of a robot is provided. A machine learning device includes: an input data acquisition means that acquires, as input data, operation data including a measurement value related to a movement of at least a portion of a body of the operator and a shape of the body, detected when the operator is caused to perform a predetermined operation associated with a training operation panel of the robot controller; a label acquisition means that acquires identification information of the operator as a label; and a learning means that constructs a learning model that performs user identification for authenticating operators of the robot controller by performing supervised learning using a pair of the input data and the label as training data.

Abstract: An apparatus can include a first state machine engine configured to receive a first portion of a data stream from a processor and a second state machine engine configured to receive a second portion of the data stream from the processor. The apparatus includes a buffer interface configured to enable data transfer between the first and second state machine engines. The buffer interface includes an interface data bus coupled to the first and second state machine engines. The buffer interface is configured to provide data between the first and second state machine engines.

Abstract: Methods and systems for training a neural network for defect detection in low resolution images are provided. One system includes an inspection tool that includes high and low resolution imaging subsystems and one or more components that include a high resolution neural network and a low resolution neural network. Computer subsystem(s) of the system are configured for generating a training set of defect images. At least one of the defect images is generated synthetically by the high resolution neural network using an image generated by the high resolution imaging subsystem. The computer subsystem(s) are also configured for training the low resolution neural network using the training set of defect images as input. In addition, the computer subsystem(s) are configured for detecting defects on another specimen by inputting the images generated for the other specimen by the low resolution imaging subsystem into the trained low resolution neural network.

Abstract: A technique relates to communication of a quantum state. Polarization hardware is configured to receive a polarization encoded qubit and split the polarization encoded qubit into two qubits. A converter is coupled to the polarization hardware, and the converter is configured to convert the two qubits into a form suitable for a CNOT gate. The CNOT gate is configured to receive the two qubits such that a measurement result of a CNOT operation of the CNOT gate determines success of the communication of the quantum state.

Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains a hierarchical representation containing a set of namespaces of a set of features shared by a set of statistical models. Next, the system uses the hierarchical representation to obtain, from one or more execution environments, a subset of the features for use in calculating the derived feature. The system then applies a formula from the hierarchical representation to the subset of the features to produce the derived feature. Finally, the system provides the derived feature for use by one or more of the statistical models.

Abstract: A system, method and a computer program product may be provided for automatically creating and parameterizing a semantically-enriched diagnosis model for an entity. The system receives a list of data points, from sensors or a database, to be used to create a diagnosis model. The system automatically creates the diagnosis model based on the received list of data points and data stored in a database and parameterizes the diagnosis model. The parameterized diagnosis model reflects rules that determine one or more potential causes of one or more abnormalities of one or more physical conditions in the entity.

Abstract: A method is provided of initializing a chip having synaptic NVRAM cells connected row-wise by word lines and column-wise by bit lines. The method includes selecting each word line through a row decoder connected to all word lines to switch all synaptic NVRAM cells of the selected lines. The method includes driving, on the selected lines, a wave generated by a PLL circuit connected to the row decoder. The method includes generating standing waves from the wave on the selected lines by implementing a resonance detection point at an input end of each word line. The method includes applying a write voltage on all bit lines through a column decoder connected to all bit lines. The method includes simultaneously driving each of the synaptic NVRAM cells of the selected lines by different writing currents for different durations in order to set different analog values to the synaptic NVRAM cells.

Abstract: A method is provided of initializing a chip having synaptic NVRAM cells connected row-wise by word lines and column-wise by bit lines. The method includes driving, on selected word lines from among the word lines, a wave generated by a PLL circuit. The method includes generating standing waves from the wave on the selected lines by implementing a resonance detection point at an input end of each word line. The method includes applying a write voltage on all bit lines. The method includes simultaneously driving each of the synaptic NVRAM cells of the selected lines by different writing currents for different durations in order to set different analog values to the synaptic NVRAM cells.

Abstract: An electronic apparatus and a control method thereof are provided. The control method includes: receiving video data; acquiring a plurality of feature information representing an object from the received video data using a plurality of filters; detecting the object included in the video data using feature information, among the plurality of feature information, acquired by at least two of the plurality of filters; and providing information on the detected object. As a result, the electronic apparatus can accurately detect surrounding vehicles and pedestrians even under a general road condition, dark road conditions (such as at night time and bad weather), or the like.

Abstract: Method of determining a likelihood of cancer relapse in a subject who has completed cancer tumor surgery, radiotherapy treatment and/or chemotherapy treatment comprises contacting an antibody that binds specifically to a serum form of thymidine kinase 1 (STK1) protein with a blood serum sample one to six months after completing the surgery and/or treatment, and before any cancer relapse has been detected; determining an amount of antibody binding to STK1 protein in the sample; correlating the amount of antibody binding to STK1 protein to a concentration of STK1 protein in the sample; and based on the concentration of STK1 protein in the sample, generating decision support information representative of a likelihood of cancer relapse in the subject one to ten years after completion of the surgery and/or treatment, the decision support information comprising a likelihood value defining one of a high or low likelihood of cancer relapse.

Abstract: Apparatus and associated methods relate to using a high learning rate to speed up the training of a receiver and switching from a high learning rate to a low learning rate for fine tuning based on exponentially weighted moving average convergence. In an illustrative example, a selection circuit may switch the high learning rate to the low learning rate based on a comparison of a moving average difference en to a predetermined stability criteria T1 of the receiver. The moving average difference en may include an exponentially weighted moving average of a difference between two consecutive exponentially weighted moving averages of an operation parameter un of the signal communication channel. By using this method, the training time for the receiver may be advantageously reduced.

Abstract: An indication of a problem within the computing environment can be received by a data processing system external to a computing environment. Based on the indication of the problem within the computing environment, the data processing system can select a data log filter. The data log filter can be configured to access, from each of a plurality of data logs, a respective data set comprising log entries that are candidate indicators of the problem. Each of the plurality of data logs can be generated by a respective electronic device that is a member of the computing environment. The data processing system can access the respective data sets from the plurality of data logs using the data log filter, and output each respective data set.

Abstract: Methods and apparatuses for determining a domain of a sentence are disclosed. The apparatus may generate, using an autoencoder, an embedded feature from an input feature indicating an input sentence, and determine a domain of the input sentence based on a location of the embedded feature in an embedding space where embedded features are distributed.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing parallel generation of output from an autoregressive sequence to sequence model. In one aspect, a blockwise parallel decoding method takes advantage of the fact that some architectures can score sequences in sublinear time. By generating predictions for multiple time steps at once then backing off to a longest prefix validated by the scoring model, the methods can substantially improve the speed of greedy decoding without compromising performance.

Abstract: An event-driven neural network includes a plurality of interconnected core circuits is provided. Each core circuit includes an electronic synapse array has multiple digital synapses interconnecting a plurality of digital electronic neurons. A synapse interconnects an axon of a pre-synaptic neuron with a dendrite of a post-synaptic neuron. A neuron integrates input spikes and generates a spike event in response to the integrated input spikes exceeding a threshold. Each core circuit also has a scheduler that receives a spike event and delivers the spike event to a selected axon in the synapse array based on a schedule for deterministic event delivery.

Abstract: A machine learning device includes a state observation unit for observing state variables that include at least one of the state of an assembly constituted of first and second components, an assembly time and information on a force, the result of a continuity test on the assembly, and at least one of position and posture command values for at least one of the first and second components and direction, speed and force command values for an assembly operation; and a learning unit for learning, in a related manner, at least one of the state of the assembly, the assembly time and the information on the force, the result of the continuity test on the assembly, and at least one of the position and posture command values for at least one of the first and second components and the direction, speed and force command values for the assembly operation.

Abstract: A method for estimating confidence bounds for adjusted rainfall values for a set of geo-locations using agricultural data comprises using a server computer system that receives, via a network, agricultural data records that are used to estimate rainfall values for the set of geo-locations. Within the server computer system, rainfall calculation instructions receive digital data including observed radar and rain-gauge agricultural data records. The computer system then aggregates the agricultural data records and creates and stores the agricultural data sets. The agricultural data records are then used to estimate adjusted rainfall values for a set of geo-locations. Rainfall confidence bounds instructions estimate a set of confidence bounds for each of the adjusted rainfall values for the set of geo-locations. The set of confidence bounds provide a range for each of the adjusted rainfall values that represents a particular level of confidence associated with each of the adjusted rainfall values.

Abstract: Internet routers are a key component in today's Internet. Each router forwards received packets toward their final destinations based upon a Longest Prefix Matching (LPM) algorithm select an entry from a routing table that determines the closest location to the final packet destination among several candidates. Prior art solutions to LPM lookup offer different tradeoffs and that it would be beneficial for a design methodology that provides for low power large scale IP lookup engines addressing the limitations within the prior art. According to embodiments of the invention a low-power large-scale IP lookup engine may be implemented exploiting clustered neural networks (CNNs). In addition to reduced power consumption embodiments of the invention provide reduced transistor count providing for reduced semiconductor die footprints and hence reduced die cost.

Abstract: A method for improving cascade classifier ordering is described. In one embodiment, the method may include determining an efficacy rating of a first current configuration, generating a decreasing sequence of values for a control parameter, and selecting a current value of the control parameter according to the decreasing sequence of values. In some cases, the method may include randomly selecting a first test configuration among the plurality of configurations based at least in part on the current value of the control parameter, analyzing the first test configuration in relation to the first current configuration, and implementing, based at least in part on the analyzing of the first test configuration, the first test configuration in a machine learning classification system of a computing device to improve a data classification accuracy of the computing device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. In one aspect, one of the systems includes an encoder neural network configured to receive the input sequence and generate encoded representations of the network inputs, the encoder neural network comprising a sequence of one or more encoder subnetworks, each encoder subnetwork configured to receive a respective encoder subnetwork input for each of the input positions and to generate a respective subnetwork output for each of the input positions, and each encoder subnetwork comprising: an encoder self-attention sub-layer that is configured to receive the subnetwork input for each of the input positions and, for each particular input position in the input order: apply an attention mechanism over the encoder subnetwork inputs using one or more queries derived from the encoder subnetwork input at the particular input position.

Abstract: A method of operating a price estimation system includes obtaining service requests from consumers, and obtaining bids from service professionals based on the service requests obtained from the consumers. The method additionally includes generating a training set based on the bids and the service requests, and generating a model for generating price estimates based on the training set. The method also includes employing the model to generate the price estimates based on additional service requests provided by additional consumers. In some aspects, the method further includes communicating the price estimates to the additional consumers during performance of a process for obtaining the additional service requests from the additional consumers. In other aspects, the method further includes communicating the price estimates to additional service professionals during performance of a process for obtaining additional bids from the additional service professionals based on the additional service requests.

Abstract: A method of producing dynamic controllable data composites from two or more data segments includes: building or training one or more function mappers to map between one or more extracted feature envelopes sets from the original data and one or more general parametric representations of the data; combining the extracted feature envelopes or the function mappers using two or more audio segments; and feeding the extracted feature envelopes or combined feature envelopes to the function mappers to obtain synthesis parameters to drive a synthesis process.

Abstract: A learning method for extracting features from an input image by hardware optimization using n blocks in a convolutional neural network (CNN) is provided. The method includes steps of: a learning device instructing a first convolutional layer of a k-th block to elementwise add a (1_1)-st to a (k_1)-st feature maps or their processed feature maps, and instructing a second convolutional layer of the k-th block to generate a (k_2)-nd feature map; and feeding a pooled feature map, generated by pooling an ROI area on an (n_2)-nd feature map or its processed feature map, into a feature classifier; and instructing a loss layer to calculate losses by referring to outputs of the feature classifier and their corresponding GT. By optimizing hardware, CNN throughput can be improved, and the method becomes more appropriate for compact networks, mobile devices, and the like. Further, the method allows key performance index to be satisfied.

Abstract: Systems, methods, and computer-readable storage devices for reducing the amount of management ports (and associated cabling) for a top-of-rack server environment. Whereas other server management configurations have cabling connecting each node in multiple multi-node chassis in a server rack to a top-of-rack, systems configured as described herein designate a single node as a point of communication for the multi-node chassis. The designated node forwards communications for all nodes in the chassis to a chassis management controller, which acts as a distribution point for all communications within the multi-node chassis, with the benefit of only a single connection being required between the multi-node chassis and the top of rack switch.

Abstract: Executing a neural network includes generating an output tile of a first layer of the neural network by processing an input tile to the first layer and storing the output tile of the first layer in an internal memory of a processor. An output tile of a second layer of the neural network can be generated using the processor by processing the output tile of the first layer stored in the internal memory.

Abstract: Examples described herein involve detecting known impairments or other known conditions using a neural network. An example implementation receives a response matrix that represents, in respective dimensions, responses of a given playback device under respective iterations of a sound captured by a recording device, the iterations including first iterations with respective impairments to the recording device and second iterations without the respective impairments to the recording device. The implementation determines principle components representing the axes of greatest variance in the response matrix, a principle-component matrix that represents a given set of the principle components, and a teaching matrix by projecting the principle-component onto the response matrix.

Abstract: Generating a computing specification to be executed by a quantum processor includes: accepting a problem specification that corresponds to a second-quantized representation of a fermionic Hamiltonian, and transforming the fermionic Hamiltonian into a first qubit Hamiltonian including a first set of qubits that encode a fermionic state specified by occupancy of spin orbitals. An occupancy of any spin orbital is encoded in a number of qubits that is logarithmic in the number of spin orbitals, and a parity for a transition between any two spin orbitals is encoded in a number of qubits that is logarithmic in the number of spin orbitals. An eigenspectrum of a second qubit Hamiltonian, including the first set of qubits and a second set of qubit, includes a low-energy subspace and a high-energy subspace, and an eigenspectrum of the first qubit Hamiltonian is approximated by a set of low-energy eigenvalues of the low-energy subspace.

Abstract: A method for learning an object detector based on a region-based convolutional neural network (R-CNN) capable of converting modes according to aspect ratios or scales of objects is provided. The aspect ratio and the scale of the objects including traffic lights may be determined according to characteristics, such as distance from the object detector, shapes, and the like, of the object. The method includes steps of: a learning device instructing an RPN to generate ROI candidates; instructing pooling layers to output feature vector; and learn the FC layers and the convolutional layer through backpropagation. In this method, pooling processes may be performed depending on real ratios and real sizes of the objects by using distance information and object information obtained through a radar, a lidar or other sensors. Also, the method can be used for surveillance as humans at a specific location have similar sizes.

Abstract: An aspect of the present invention is to provide a system and method for predicting the remaining useful time of mechanical components such as bearings. Another aspect of the present invention is to provide a system and method for predicting the remaining useful time of bearings based on available condition monitoring data. Another aspect of the present invention is to provide a system and method for automatically deciding which columns of input information are the most significant for predicting the remaining useful life of bearings. Another aspect of the present invention is to provide a system and method for performing an analysis of both test bearings and training bearings and determining which training bearings are most similar to a given test bearing. Another aspect of the present invention is to provide a system and method for training an artificial neural network.

Abstract: Provided is a process, including: obtaining a first training dataset of subject-entity records; training a first machine-learning model on the first training dataset; forming virtual subject-entity records by appending members of a set of candidate action sequences to time-series of at least some of the subject-entity records; forming a second training dataset by labeling the virtual subject-entity records with predictions of the first machine-learning model; and training a second machine-learning model on the second training dataset.

Abstract: A compression coding apparatus for artificial neural network, including memory interface unit, instruction cache, controller unit and computing unit, wherein the computing unit is configured to perform corresponding operation to data from the memory interface unit according to instructions of controller unit; the computing unit mainly performs three steps operation: step one is to multiply input neuron by weight data; step two is to perform adder tree computing and add the weighted output neuron obtained in step one level-by-level via adder tree, or add bias to output neuron to get biased output neuron; step three is to perform activation function operation to get final output neuron. The present disclosure also provides a method for compression coding of multi-layer neural network.

Abstract: A front-end system collects user attribute value data and organizes the data into one or more training data sets and one or more test data sets. The front-end system provides at least some of the test data sets to an input layer of a machine learning system. Within the machine learning system, one or more predictive models are constructed. At an output layer, the predictive models provide output data that includes at least a value indicative of whether a user will upgrade service levels based at least in part on the attribute values logically associated with the respective user. A back-end system generates upgrade offers for subsequent communication to those users identified as being likely to upgrade.

Abstract: A method is provided for estimating past data by identifying a high frequency data set for a defined time period. A pattern is calculated for the high frequency data set and then the pattern is applied to a low frequency data set in a past time period to estimate a high frequency query point.

Abstract: A machine provides a system and interface to deploy and manage pre-defined analytical models across various compute engines or run time environments, e.g., by exposing analytical model deployment and management parameters to a user while abstracting model deployment activities. The machine also determines proper run time environments for the pre-defined analytical model and verifies the pre-defined analytical model. The machine also provides a dynamically reconfigurable user interface for controlling the machine.

Abstract: A processor includes a front end to decode an instruction, an allocator to pass the instruction to a nearest neighbor logic unit (NNLU) to execute the instruction, and a retirement unit to retire the instruction. The NNLU includes logic to determine input of the instruction for which nearest neighbors will be calculated, transform the input, retrieve candidate atoms for which the nearest neighbors will be calculated, compute distance between the candidate atoms and the input, and determine the nearest neighbors for the input based upon the computed distance.

Abstract: As provided herein, a list of locales of interest in a location may be sorted into one or more categories. A user performing a search for a locale of interest (e.g., a restaurant) may be identified. A local score may be assigned to the locale of interest based upon a number of local users (e.g., users residing in the location) that perform the search. A second user may be determined to be near the locale of interest. A category of interest may be determined for the second user (e.g., an interest in local non-tourist restaurants). Responsive to the category of interest corresponding to the category and the local score of the locale of interest exceeding an interest threshold, the second user may be provided with a recommendation to go to the locale of interest. The locale of interest may be a local favorite restaurant rather than a tourist trap.

Abstract: A system and method for characterizing surfaces includes using a measuring device to take size measurements of a manufactured product. The raw measurement data is transformed from a time-based domain to a frequency-based domain using a mathematical algorithm. The transformed size measurement data is then compared to predetermined limits within comparable frequency bands to characterize the surface of the manufactured product.

Abstract: An artificial neuron unit comprising one artificial neuron having at least one output port and at least one input port, and one memristor having two terminals; said unit being characterized in that it also comprises at least one current conveyor having two input ports X and Y, and one output port Z; and in which said memristor is connected by one of its terminals to the input port X of said current conveyor, said current conveyor is connected by its output port Z to an input port of said artificial neuron and said artificial neuron is connected by one of its output ports to the input port Y of said current conveyor or to another of said terminals of said memristor.

Abstract: In general, embodiments of the present invention provide systems, methods and computer readable media for automated dynamic data quality assessment. One aspect of the subject matter described in this specification includes the actions of receiving a data quality job including a new data sample; and, if the new data sample is determined to be added to a reservoir of data samples, sending a quality verification request to an oracle; receiving a new data sample quality estimate from the oracle; and adding the new data sample and estimate to the reservoir. A second aspect of the subject matter includes the actions of receiving, from a predictive model, a judgment associated with a new data sample; analyzing the new data sample based in part on the judgment to determine whether to send a new data sample quality verification request to an oracle; and, if a new data sample quality estimate is received from the oracle, determining whether to add the new data sample and the judgment to the reservoir.