Abstract: A method comprises a first block of memory cells to store an input array, and a second block of memory cells. Pooling circuitry is operatively coupled to the first block of memory cells to execute in-place pooling according to a function over the input array to generate an array of output values. Writing circuitry is operatively coupled to the second block to store the array of output values in the second block of memory cells. Analog sensing circuitry is coupled to the first block of memory cells to generate analog values for the input array, wherein the pooling circuitry receives the analog values as inputs to the function. The writing circuitry operatively coupled to the second block is configured to store an analog level in each cell of the second block for the array of output values.

Abstract: Various face discrimination systems may benefit from techniques for providing increased accuracy. For example, certain discriminative face verification systems can benefit from L2-constrained softmax loss. A method can include applying an image of a face as an input to a deep convolutional neural network. The method can also include applying an output of a fully connected layer of the deep convolutional neural network to an L2-normalizing layer. The method can further include determining softmax loss based on an output of the L2-normalizing layer.

Abstract: A method includes determining, by a vehicle, a failure with a computer or telecommunications system operating in the vehicle and when a failure is detected, activating an acoustic system on the vehicle, detecting a vibration by the vehicle; and transmitting an audible signal responsive to the detecting step. The audible signal may include words in a human vocabulary.

Abstract: Compact representation for input workloads is generated in a memory system, A memory controller includes firmware (FW) and an encoder including recurrent encoding blocks. Each recurrent encoding block receives one of input commands in an input workload, and generates a hidden state vector corresponding to the received input command by applying a set of activation functions on the received input command. The last encoding block generates a final hidden state vector as a compact representation vector corresponding to the input commands. The firmware determines a distance function between the compact representation vector and each of multiple compact workload vectors and tunes at least one of firmware parameters based on the determined distances.

Abstract: A learning apparatus includes: an update unit which updates a dictionary used by a classifier; a calculation unit which calculates, by using a dictionary updated and one or more samples with labeling being samples assigned with labels, a ratio to a number of the samples with labeling as a loss with respect to all the samples with labeling; and a determination unit which determines whether to update the dictionary, by using the loss, wherein, when the determination unit determines to update the dictionary, the update unit updates the dictionary by using the samples with labeling added with a new sample with labeling, and wherein the determination unit determines whether to update the dictionary, by using a loss calculated by using the updated dictionary and a loss calculated by using the dictionary before updating with respect to all the samples with labeling before adding the new sample with labeling.

Abstract: A method for automatically training a neural network includes at a trainer having a first communication device and a perception recorder, continuously recording the surroundings in the vicinity of the first object; receiving, at the trainer, a message from a communication device associated with an object in the vicinity of the trainer, the message including information about the position and the type of the object; identifying a recording corresponding to the time at which the message is received from the object; correlating the received positional information about the second object with a corresponding location in the recording to identify the object in the recording; classifying the identified object based on the type of information received in the message from the object; and using the classified recording to train the neural network.

Abstract: Proposed are a method and apparatus for accelerating data processing in a neural network. The apparatus for accelerating data processing in a neural network may include: a control unit configured to quantize data by at least one method according to a characteristic of data calculated at a node forming at least one layer constituting the neural network, and to separately perform calculation at the node according to the quantized data; and memory configured to store the quantized data.

Abstract: A method for determining the performance metric of a function may include interpolating the performance metric of the function relative to a known performance metric of a reference function. The performance metric of the function may be interpolated based on a first difference in a performance of the function measured by applying a first machine learning model and a performance of the function measured by applying a second machine learning model. The performance metric of the function may be further interpolated based on a second difference in a performance of the reference function measured by applying the first machine learning model and a performance of the reference function measured by applying the second machine learning model. The function may be deployed to a production system if the performance metric of the function exceeds a threshold value. Related systems and articles of manufacture, including computer program products, are also provided.

Abstract: According to a method and apparatus for neural network quantization, a quantized neural network is generated by performing learning of a neural network, obtaining weight differences between an initial weight and an updated weight determined by the learning of each cycle for each of layers in the first neural network, analyzing a statistic of the weight differences for each of the layers, determining one or more layers, from among the layers, to be quantized with a lower-bit precision based on the analyzed statistic, and generating a second neural network by quantizing the determined one or more layers with the lower-bit precision.

Abstract: Techniques for estimating the number of distinct values in a data set using machine learning are provided. In one technique, a sample of a data set is retrieved where the sample is a strict subset of the data set. The sample is analyzed to identify feature values of multiple features of the sample. The feature values are inserted into a machine-learned model that computes a prediction regarding a number of distinct values in the data set. An estimated number of distinct values that is based on the prediction is stored in association with the data set.

Abstract: A processor includes a register, a non-zero weight value selector and a multiplier. The register holds a first group of weight values and a second group of weight values. Each group of weight values includes at least one weight value, and each weight value in the first group of weight values corresponding to a weight value in the second group of weight values. The non-zero weight value selector selects a non-zero weight value from a weight value in the first group of weight values or a non-zero weight value in the second group of weight values that corresponds to the weight value in the first group of weight values. The multiplier multiplies the selected non-zero weight value and an activation value that corresponds to the selected non-zero weight value to form an output product value.

Abstract: A heterogeneous processing system includes at least one central processing unit (CPU) core and at least one graphics processing unit (GPU) core. The heterogeneous processing system is configured to compute an activation for each one of a plurality of neurons for a first network layer of a neural network. The heterogeneous processing system randomly drops a first subset of the plurality of neurons for the first network layer and keeps a second subset of the plurality of neurons for the first network layer. Activation for each one of the second subset of the plurality of neurons is forwarded to the CPU core and coalesced to generate a set of coalesced activation sub-matrices.

Abstract: Systems, methods, and apparatuses are provided for compressing values. A plurality of parameters may be obtained from a memory, each parameter comprising a floating-point number that is used in a relationship between artificial neurons or nodes in a model. A mantissa value and an exponent value may be extracted from each floating-point number to generate a set of mantissa values and a set of exponent values. The set of mantissa values may be compressed to generate a mantissa lookup table (LUT) and a plurality of mantissa LUT index values. The set of exponent values may be encoded to generate an exponent LUT and a plurality of exponent LUT index values. The mantissa LUT, mantissa LUT index values, exponent LUT, and exponent LUT index values may be provided to one or more processing entities to train the model.

Abstract: In one aspect, a method includes generating a functional subgraph of a network from a structural graph of the network. The structural graph comprises a set of vertices and structural connections between the vertices. Generating the functional subgraph includes identifying a directed functional edge of the functional subgraph based on presence of structural connection and directional communication of information across the same structural connection.

Abstract: A process for discovering optimal Generative Adversarial Networks (GAN) includes jointly optimizing the three functions of a GANs process including (i) a real component of a discriminator network's loss that is a function of D(x), wherein D(x) is the discriminator network's output for a real sample from an input dataset; (ii) a synthetic component of the discriminator network's loss that is a function of D(G(z)), wherein D(G(z)) is the discriminator network's output for a generator network's synthetic samples z from a latent distribution; and (iii) a generator network's loss which is a function of D(G(z)), with the discriminator network's total loss being the sum of components (i) and (ii).

Abstract: A cascaded machine learning inference system and method is disclosed. The cascaded system and method may be designed to be employed in resource restricted environments. The cascaded system and method may be applicable for applications that operate with limited power (e.g., a wearable smart watch). The cascaded system and method may employ two or more subsystems that are operable to classify an input signal provided by any number or types of sensors suitable for a given application. For instance, the sensors used may include gyroscopes, accelerometers, magnetometers, or barometric altimeters. The system and method may also be further split functionality across additional or new subsystems. By splitting operations and functionality across additional subsystems, the overall power consumption may further be reduced.

Abstract: According to an aspect, a method includes receiving a first three-dimensional model (3D) model of at least a body part of a person, receiving a second 3D model of a wearable device, and predicting, by at least one machine-learning (ML) model, a plurality of contact points between the first 3D model and the second 3D model.

Abstract: At an artificial intelligence system, a respective feature set is generated from individual text collections pertaining to an item, using a first machine learning model which is trained to perform character-level analysis. Using at least a portion of a second machine learning model, a score associated with a semantic criterion is generated for an item; the training input to the second model is based on the feature sets. A recommendation associated with the item is generated based on the score.

Abstract: Disclosed is neural network circuitry having a first plurality of logic cells that is interconnected to form neural network computation units that are configured to perform approximate computations. The neural network circuitry further includes a second plurality of logic cells that is interconnected to form a controller hierarchy that is interfaced with the neural network computation units to control pipelining of the approximate computations performed by the neural network computational units. In some embodiments the neural network computation units include approximate multipliers that are configured to perform approximate multiplications that comprise the approximate computations. The approximate multipliers include preprocessing units that reduce latency while maintaining accuracy.

Abstract: Graphical elements in a user interface (UI) may be detected in robotic process automation (RPA) using convolutional neural networks (CNNs). Such processes may be particularly well-suited for detecting graphical elements that are too small to be detected using conventional techniques. The accuracy of detecting graphical elements (e.g., control objects) may be enhanced by providing neural network-based processing that is robust to changes in various UI factors, such as different resolutions, different operating system (OS) scaling factors, different dots-per-inch (DPI) settings, and changes due to UI customization of applications and websites, for example.

Abstract: Disclosed is a technique that can be performed by a server computer system. The technique can include obtaining data from each of multiple endpoint devices to form global data. The global data can be generated by the endpoint devices in accordance with local instructions in each of the endpoint devices. The technique further includes generating global instructions based on the global data and sending the global instructions to a particular endpoint device. The global instructions configure the particular endpoint device to perform a data analytic operation that analyzes events. The events can include raw data generated by a sensor of the particular endpoint device.

Abstract: A method, an electronic device, and computer readable medium are provided. The method includes receiving an input into a neural network that includes a kernel. The method also includes generating, during a convolution operation of the neural network, multiple panel matrices based on different portions of the input. The method additionally includes successively combining each of the multiple panel matrices with the kernel to generate an output. Generating the multiple panel matrices can include mapping elements within a moving window of the input onto columns of an indexing matrix, where a size of the window corresponds to the size of the kernel.

Abstract: A computer architecture for multiplier-less machine learning is disclosed. According to some aspects, a neural network apparatus include processing circuitry and memory. The processing circuitry accesses a plurality of weights for a neural network layer and an input vector for the neural network layer, the input vector comprising a plurality of data values. The processing circuitry provides the plurality of weights and the input vector to an addition layer. The addition layer generates data value-weight pairs and, for each data value-weight pair, creates an input block comprising a sum of the data value and the weight. The processing circuitry sorts the input blocks generated by the addition layer. The processing circuitry cancels any opposite signed input blocks from the sorted input blocks to generate a set of blocks. The processing circuitry outputs a Kth largest value from the set of blocks. K is a positive integer.

Abstract: Systems and methods for classifying radio frequency signal modulations include receiving, at a consolidated neural network, a complex quadrature vector of interest representative of a baseband signal derived from a radio frequency signal, generating multiple data representations of the vector of interest, providing each data representation to one of multiple parallel neural networks in the consolidated neural network, and receiving, from the consolidated neural network, a classification result for the baseband signal.

Abstract: The present disclosure advantageously provides a hardware accelerator for an artificial neural network (ANN), including a communication bus interface, a memory, a controller, and at least one processing engine (PE). The communication bus interface is configured to receive a plurality of finetuned weights associated with the ANN, receive input data, and transmit output data. The memory is configured to store the plurality of finetuned weights, the input data and the output data. The PE is configured to receive the input data, execute an ANN model using a plurality of fixed weights associated with the ANN and the plurality of finetuned weights, and generate the output data. Each finetuned weight corresponds to a fixed weight.

Abstract: A method and a system for converting a font of a Chinese character in an image, a computer device and a medium are disclosed. A specific implementation of the method includes: acquiring a stroke of a to-be-converted Chinese character in the image and spatial distribution information of the stroke; and generating a Chinese character in a target font that corresponds to the to-be-converted Chinese character in the image according to the stroke of the to-be-converted Chinese character, the spatial distribution information of the stroke and standard stroke information of the target font, to replace the to-be-converted Chinese character.

Abstract: An apparatus for driving a motor includes motor circuitry and neural network circuitry. The motor circuitry is configured to generate, based on an error compensated rotor angle and current at a plurality of phases of the motor, a d-axis instant current value and generate a d-axis instant voltage value based on the d-axis instant current value. The motor circuitry is further configured to generate voltage at the plurality of phases based on the d-axis instant voltage value. The neural network circuitry is configured to generate a rotor angle offset based on an instant rotor speed at the motor. The neural network circuitry has been trained to generate the rotor angle offset to minimize the d-axis instant voltage value for each of a plurality of rotor speeds at the motor. The error compensated rotor angle is based on the rotor angle offset.

Abstract: Embodiments relate to a neural engine circuit that includes an input buffer circuit, a kernel extract circuit, and a multiply-accumulator (MAC) circuit. The MAC circuit receives input data from the input buffer circuit and a kernel coefficient from the kernel extract circuit. The MAC circuit contains several multiply-add (MAD) circuits and accumulators used to perform neural networking operations on the received input data and kernel coefficients. MAD circuits are configured to support fixed-point precision (e.g., INT8) and floating-point precision (FP16) of operands. In floating-point mode, each MAD circuit multiplies the integer bits of input data and kernel coefficients and adds their exponent bits to determine a binary point for alignment. In fixed-point mode, input data and kernel coefficients are multiplied. In both operation modes, the output data is stored in an accumulator, and may be sent back as accumulated values for further multiply-add operations in subsequent processing cycles.

Abstract: Embodiments relate to a method and system for determining a situation of a facility by imaging a sensing data of the facility including receiving sensing data through a plurality of sensors at a query time, generating a situation image at the query time, showing the situation of the facility at the query time based on the sensing data, and determining if an abnormal situation occurred at the query time by applying the situation image to a pre-learned situation determination model.

Abstract: Artificial intelligence decision making neuro network core system and information processing method using the same include an electronic device linking to a unsupervised neural network interface module, a asymmetric hidden layers input module linking to the unsupervised neural network interface module and a neuron module formed with tree-structured data, a layered weight parameter module linking to the neuron module formed with tree-structured data and an non-linear PCA (Principal Component Analysis) module, an input module of the lead backpropagation unit linking to the non-linear PCA module and a tuning module, an output module of the lead backpropagation unit linking to tuning module and the non-linear PCA module; when the electronic device receives raw data, processing and learning the raw data via all the modules, and updating programs to generate decision results that accommodate a variety of scenarios, in order to elevate the reference value and practicality of the decision result.

Abstract: The present disclosure is directed to a system for reparameterizing of a neural network to optimize structural designs. The system can obtain data descriptive of a design space for a physical design problem. The design space is parameterized by a first set of parameters. The system can reparameterize the design space with a machine-learned model that comprises a second set of parameters. For a plurality of iterations, the system can provide an input to the machine-learned model to produce a proposed solution. The system can apply one or more design constraints to the solution to create a constrained solution. The system can generate a physical outcome associated with the constrained solution using a physical model. The system can evaluate the physical outcome using an objective function and update at least one of the second set of parameters. After the plurality of iterations, the system can output a solution.

Abstract: Techniques are described herein for robotic control using value distributions. In various implementations, as part of performing a robotic task, state data associated with the robot in an environment may be generated based at least in part on vision data captured by a vision component of the robot. A plurality of candidate actions may be sampled, e.g., from continuous action space. A trained critic neural network model that represents a learned value function may be used to process a plurality of state-action pairs to generate a corresponding plurality of value distributions. Each state-action pair may include the state data and one of the plurality of sampled candidate actions. The state-action pair corresponding to the value distribution that satisfies one or more criteria may be selected from the plurality of state-action pairs. The robot may then be controlled to implement the sampled candidate action of the selected state-action pair.

Abstract: Systems, devices, and methods related to a Deep Learning Accelerator and memory are described. For example, a wearable electronic device may be configured to execute instructions with matrix operands and configured with: a housing to be worn on a person; a sensor having one or more sensor elements generate measurements associated with the person; random access memory to store instructions executable by the Deep Learning Accelerator and store matrices of an Artificial Neural Network; a transceiver; and a controller to monitor an output of the Artificial Neural Network, generated using the measurements as an input to the Artificial Neural Network. Based on the output, the controller may control selective storage of measurement data from the sensor, and/or selective communication of data from the wearable electronic device to a separate computer system.

Abstract: A low-power, controllable, and reconfigurable method to control weights in model neurons in an Artificial Neural Network is disclosed. Memristors are utilized as adjustable synapses, where the memristor resistance reflects the synapse weight. The injection of extremely small electric currents (a few nanoamperes) in each cell forces the resistance to drop abruptly by several orders of magnitudes due to the formation of a conductive path between the two electrodes. These conductive paths dissolve as soon as the current injection stops, and the cells return to their initial state. A repeated injection of currents into the same cell results in an almost identical effect in resistance drop. Different, stable resistance values in each cell can be controllably achieved by injecting different current values.

Abstract: A method and an apparatus for adapting feature data in a convolutional neural network. The method includes selecting a plurality of consecutive layers; determining an expected number of subdata blocks and a layout position, width and height of each subdata block in an output feature data of a last layer; determining, for each current layer, a layout position, width, and height of each subdata block of an input feature data for the current layer according to the layout position, width, and height of each subdata block of the output feature data for the current layer; determining an actual position of each subdata block of the input feature data for a first layer in the input feature data for the first layer; and obtaining the expected number of subdata blocks of the input feature data for the first layer according to the actual position, width and height of each subdata block of the input feature data for the first layer.

Abstract: Disclosed is an artificial intelligence or machine learning algorithm that may be applied to a plurality of machine learning devices in a 5G environment connected to perform the Internet of things. A machine learning method by a first learning machine according to one embodiment of the present disclosure may include obtaining input data; determining, from among a plurality of clusters, a cluster to which the input data belongs, by using a first artificial neural network; transmitting a plurality of sample features associated with the determined cluster to a second learning device using a second artificial neural network; receiving a label for the plurality of sample features from the second learning device, in response to the transmission; and associating the received label with the determined cluster.

Abstract: Cache memory requirements between normal and peak operation may vary by two orders of magnitude or more. A cache memory management system for multi-tenant computing environments monitors memory requests and uses a pattern matching classifier to generate patterns which are then delivered to a neural network. The neural network is trained to predict near-future cache memory performance based on the current memory access patterns. An optimizer allocates cache memory among the tenants to ensure that each tenant has sufficient memory to meet its required service levels while avoiding the need to provision the computing environment with worst-case scenario levels of cache memory. System resources are preserved while maintaining required performance levels.

Abstract: An apparatus identifies partial tensor data that contributes to machine learning using tensor data in a tensor format obtained by transforming training data having a graph structure. Based on the partial tensor data and the training data, the apparatus generates expanded training data to be used in the machine learning by expanding the training data.

Abstract: A neuromorphic system includes an address translation device that translates an address corresponding to each of synaptic weights between presynaptic neurons and postsynaptic neurons to generate a translation address, and a plurality of synapse memories that store the synaptic weights based on the translation address. The translation address is generated such that at least two of synaptic weights corresponding to each of the postsynaptic neurons are stored in different synapse memories of the plurality of synapse memories and such that at least two of synaptic weights corresponding to each of the presynaptic neurons are stored in different synapse memories.

Abstract: Smart sensor methods and systems are described that improve on prior systems. An example device includes a sensor, a memory, a network connection, and two processing units, wherein a first processing unit compares current data provided by the first sensor to the reference data previously provided by the first sensor. Based on the result of the comparison, a second processing unit may be enabled to process the current data, or may be disabled to prevent the second processing unit from processing the current data.

Abstract: Disclosed is a technique that can be performed by a server computer system. The technique can include obtaining data from each of multiple endpoint devices to form global data. The global data can be generated by the endpoint devices in accordance with local instructions in each of the endpoint devices. The technique further includes generating global instructions based on the global data and sending the global instructions to a particular endpoint device. The global instructions configure the particular endpoint device to perform a data analytic operation that analyzes events. The events can include raw data generated by a sensor of the particular endpoint device.

Abstract: A processor includes a register, a non-zero weight value selector and a multiplier. The register holds a first group of weight values and a second group of weight values. Each group of weight values includes at least one weight value, and each weight value in the first group of weight values corresponding to a weight value in the second group of weight values. The non-zero weight value selector selects a non-zero weight value from a weight value in the first group of weight values or a non-zero weight value in the second group of weight values that corresponds to the weight value in the first group of weight values. The multiplier multiplies the selected non-zero weight value and an activation value that corresponds to the selected non-zero weight value to form an output product value.

Abstract: A system and method of executing a convolution layer of a neural network may include: (a) selecting an output spatial position (OSP) of an output matrix data element of the convolution layer; (b) selecting, based on the selected OSP, a non-zero input element of an input matrix data element; (c) producing, based on the selected OSP, a vector of kernel elements from a kernel matrix data element; (d) performing a vectoral multiplication operation of the selected non-zero input element and the vector of kernel elements, and accumulating a product of the vectoral multiplication in a vector register of a processor; (e) repeating (c) and (d) with subsequent non-zero input elements and corresponding vectors of kernel elements to obtain an outcome of the convolution of the selected OSP; and (f) repeating (a) through (e) with subsequent selection of OSPs, to obtain an outcome of the convolution layer.

Abstract: A system may include a processor that may execute computer-executable instructions that cause the processor to receive caller information regarding an incoming communication from a caller and receive a request from a user to route the incoming communication to a virtual assistant application. The virtual assistant application is configured to interact with the caller and determine whether the caller is associated a fraudulent caller activity stored on databases accessible by the processor. The processor may then receive an indication from the virtual assistant application that the caller is associated with the fraudulent caller activity and forward the incoming communication to another party in response to receiving the indication.

Abstract: The present invention relates to the digital circuits for evaluating neural engineering framework style neural networks. The digital circuits for evaluating neural engineering framework style neural networks comprised of at least one on-chip memory, a plurality of non-linear components, an external system, a first spatially parallel matrix multiplication, a second spatially parallel matrix multiplication, an error signal, plurality of set of factorized network weight, and an input signal. The plurality of sets of factorized network weights further comprise a first set factorized network weights and a second set of factorized network weights. The first spatially parallel matrix multiplication combines the input signal with the first set of factorized network weights called the encoder weight matrix to produce an encoded value. The non-linear components are hardware simulated neurons which accept said encoded value to produce a distributed neural activity.

Abstract: In order to help reduce the effects of motion sickness, there is provided a method for reducing motion sickness in a subject which comprises acquiring a sequence of video images, extracting measurements of a heart-rate of the subject over a first period of time from the sequence of video images using photoplethysmography (PPG), calculating at least one trend in the measurements, determining a presence of motion sickness when the at least one trend is positive over a first time window, the first time window being included in the first period of time, and generating an event arranged to generate a corrective action. It is often possible to detect the onset of motion sickness before the subject actually feels the symptoms. Indeed, by the time the symptoms appear, corrective action is much less effective. Therefore, by detecting the onset early and alerting the subject so that they can react, it is possible to avoid the attack of motion sickness or, at least, reduce significantly its effects.

Abstract: A method for designing a tool string for use in a wellbore includes receiving a merit function, and determining, with a computing system and based on the merit function, a tool string design for a tool string. The merit function comprises one or more defined objectives for performing a process in a wellbore. The tool string design comprises an indication of one or more tools used to form a tool string for performing the process in the wellbore, and the tool string design satisfies the merit function.

Abstract: Analog processors for solving various computational problems are provided. Such analog processors comprise a plurality of quantum devices, arranged in a lattice, together with a plurality of coupling devices. The analog processors further comprise bias control systems each configured to apply a local effective bias on a corresponding quantum device. A set of coupling devices in the plurality of coupling devices is configured to couple nearest-neighbor quantum devices in the lattice. Another set of coupling devices is configured to couple next-nearest neighbor quantum devices. The analog processors further comprise a plurality of coupling control systems each configured to tune the coupling value of a corresponding coupling device in the plurality of coupling devices to a coupling. Such quantum processors further comprise a set of readout devices each configured to measure the information from a corresponding quantum device in the plurality of quantum devices.

Abstract: A system and method for reducing laser communication terminal pointing uncertainty. The method trains an artificial neural network (ANN) with input data characterizing terminal pointing error and dependent parameters. The method inputs the trained ANN a set of data of these dependent parameters with unknown pointing error. The method uses the ANN output to apply corrections to the terminal pointing solution to reduce pointing uncertainty. The method can condition the ANN generated corrections to avoid cases where application of the ANN correction could exceed the original pointing uncertainty. This conditioning includes computing the Euclidean distance between current ANN input parameter values and values in the ANN training dataset, and bounding the allowed magnitude of the ANN pointing correction. The method can train the ANN incrementally during terminal operation for real-time updates or train the ANN offline with gathered data and implement the trained ANN on the terminal for subsequent links.

Abstract: Methods, systems and devices for unsupervised learning utilizing at least one kT-RAM. An evaluation can be performed over a group of N AHaH nodes on a spike pattern using a read instruction (FF), and then an increment high (RH) instruction can be applied to the most positive AHaH node among the N AHaH nodes if an ID associated with the most positive AHaH node is not contained in a set, followed by adding a node ID to the set. In addition, an increment low (RL) instruction can be applied to all AHaH nodes that evaluated positive but were not the most positive, contingent on the most-positive AHaH node's ID not being contained in the set. In addition, node ID's can be removed from the set if the set size is equal to the N number of AHaH nodes.