Abstract: One embodiment of an accelerator includes a computing unit; a first memory bank for storing input activations and a second memory bank for storing parameters used in performing computations, the second memory bank configured to store a sufficient amount of the neural network parameters on the computing unit to allow for latency below a specified level with throughput above a specified level. The computing unit includes at least one cell comprising at least one multiply accumulate (“MAC”) operator that receives parameters from the second memory bank and performs computations. The computing unit further includes a first traversal unit that provides a control signal to the first memory bank to cause an input activation to be provided to a data bus accessible by the MAC operator. The computing unit performs computations associated with at least one element of a data array, the one or more computations performed by the MAC operator.

Abstract: A segmentation platform enables a system that comprises a behavior service and a predictive service for determining a segment from a dataset. The behavior service can analyze data to determine information about behavior that has already occurred. The predictive service can analyze data to determine information about the predicted propensity for certain behavior to occur in the future. In some cases, the predictive service can determine the information by utilizing a training model that indicates predictions related to potential relationships among properties of a dataset. The segmentation platform also enables an interactive user interface that can be utilized to configure attributes of the segment, analyze information associated with the segment, and deliver the information to another device.

Abstract: To obtain one or more recommendations for the migration of a database to a cloud computing system, information about performance of the database operating under a workload may be obtained. A first machine learning model (e.g., a neural network-based autoencoder) may be used to generate a compressed representation of characteristics of the database operating under the workload. The compressed representation may then be provided as input to a second machine learning model (e.g., a neural network-based classifier), which outputs a recommendation regarding a characteristic (e.g., size, configuration, level of service) of the cloud database to which the database should be migrated. This type of recommendation may be made prior to migration, thereby making it easier to properly estimate the cost of running the cloud database and plan the migration accordingly.

Abstract: Systems and methods are provided for automatically scoring a constructed response. The constructed response is processed to generate a plurality of numerical vectors that is representative of the constructed response. A model is applied to the plurality of numerical vectors. The model includes an input layer configured to receive the plurality of numerical vectors, the input layer being connected to a following layer of the model via a first plurality of connections. Each of the connections has a first weight. An intermediate layer of nodes is configured to receive inputs from an immediately-preceding layer of the model via a second plurality of connections, each of the connections having a second weight. An output layer is connected to the intermediate layer via a third plurality of connections, each of the connections having a third weight. The output layer is configured to generate a score for the constructed response.

Abstract: Techniques described herein may be used to solve a stochastic problem by dividing the stochastic problem into multiple fragments. In some cases, each fragment may be related to a random variable that forms a part of the problem, such that each fragment may produce samples from a probability distribution for that variable. Each fragment of the stochastic problem may then be assigned to a configurable circuit to solve the stochastic fragment. Configurable circuits may be implemented using any suitable combination of hardware and/or software, including using stochastic circuitry. In some embodiments, stochastic circuitry may include a stochastic tile and/or a stochastic memory.

Abstract: A method is provided for protecting a machine learning ensemble. In the method, a plurality of machine learning models is combined to form a machine learning ensemble. A plurality of data elements for training the machine learning ensemble is provided. The machine learning ensemble is trained using the plurality of data elements to produce a trained machine learning ensemble. During an inference operating phase, an input is received by the machine learning ensemble. A piecewise function is used to pseudo-randomly choose one of the plurality of machine learning models to provide an output in response to the input. The use of a piecewise function hides which machine learning model provided the output, making the machine learning ensemble more difficult to copy.

Abstract: A neural array may include an array unit, a first processing unit, and a second processing unit. The array unit may include synaptic devices. The first processing unit may input a row input signal to the array unit, and receive a row output signal from the array unit. The second processing unit may input a column input signal to the array unit, and receive a column output signal from the array unit. The array unit may have a first array value and a second array value. When the first processing unit or the second processing unit receives an output signal based on the first array value from the array unit which has selected the first array value and then the array unit selects the second array value, it may input a signal generated based on the output signal to the array unit which has selected the second array value.

Abstract: A numerical control system detects a state amount indicating a state of an injection operation of an injection molding machine, generates a characteristic amount that characterizes the state of the injection operation from the state amount, and infers an evaluation value of the state of the injection operation from the characteristic amount. The numerical control system detects an abnormal state on the basis of the evaluation value, generates or updates a learning model by machine learning that uses the characteristic amount, and stores the learning model in correlation with a combination of conditions of the injection operation.

Abstract: Some embodiments include a special-purpose hardware accelerator that can perform specialized machine learning tasks during both training and inference stages. For example, this hardware accelerator uses a systolic array having a number of data processing units (“DPUs”) that are each connected to a small number of other DPUs in a local region. Data from the many nodes of a neural network is pulsed through these DPUs with associated tags that identify where such data was originated or processed, such that each DPU has knowledge of where incoming data originated and thus is able to compute the data as specified by the architecture of the neural network. These tags enable the systolic neural network engine to perform computations during backpropagation, such that the systolic neural network engine is able to support training.

Abstract: A mobile electronic device such as a smartphone is used in conjunction with a deep learning system to detect and respond to personal danger. The deep learning system monitors current information (such as location, audio, biometrics, etc.) from the smartphone and generates a risk score by comparing the information to a routine profile for the user. If the risk score exceeds a predetermined threshold, an alert is sent to the smartphone which presents an alert screen to the user. The alert screen allows the user to cancel the alert (and notify the deep learning system) or confirm the alert (and immediately transmit an emergency message). Multiple emergency contacts can be designated, e.g., one for a low-level risk, another for an intermediate-level risk, and another for a high-level risk, and the emergency message can be sent to a selected contact depending upon the severity of the risk score.

Abstract: Mechanisms are provided to implement a hardened neural network framework. A data processing system is configured to implement a hardened neural network engine that operates on a neural network to harden the neural network against evasion attacks and generates a hardened neural network. The hardened neural network engine generates a reference training data set based on an original training data set. The neural network processes the original training data set and the reference training data set to generate first and second output data sets. The hardened neural network engine calculates a modified loss function of the neural network, where the modified loss function is a combination of an original loss function associated with the neural network and a function of the first and second output data sets. The hardened neural network engine trains the neural network based on the modified loss function to generate the hardened neural network.

Abstract: A machine learning device which learns a correlation between shipment inspection information obtained by inspecting an object in shipment thereof and operation alarm information issued during operation of the object, includes a state observation unit which observes the shipment inspection information and the operation alarm information; and a learning unit which generates a learning model based on the shipment inspection information and the operation alarm information observed by the state observation unit.

Abstract: A method for increasing a speed or energy efficiency at which a computer is capable of modeling a plurality of random walkers. The method includes defining a virtual space in which a plurality of virtual random walkers will move among different locations in the virtual space, wherein the virtual space comprises a plurality of vertices and wherein the different locations are ones of the plurality of vertices. A corresponding set of neurons in a spiking neural network is assigned to a corresponding vertex such that there is a correspondence between sets of neurons and the plurality of vertices, wherein a spiking neural network comprising a plurality of sets of spiking neurons is established. A virtual random walk of the plurality of virtual random walkers is executed using the spiking neural network, wherein executing includes tracking how many virtual random walkers are at each vertex at a given time increment.

Abstract: Some embodiments provide a method for compiling a neural network program for a neural network inference circuit. The method receives a neural network definition including multiple weight values arranged as multiple filters. For each filter, each of the weight values is one of a set of weight values associated with the filter. At least one of the filters has more than three different associated weight values. The method generates program instructions for instructing the neural network inference circuit to execute the neural network. The neural network inference circuit includes circuitry for executing neural networks with a maximum of three different weight values per filter.

Abstract: The present disclosure relates to a computer-implemented method for routing in an electronic design. Embodiments may include receiving, using at least one processor, global route data associated with an electronic design as an input and generating detail route data, based upon, at least in part, the global route data. Embodiments may further include transforming one or more of the detail route data and the global route data into at least one input feature and at least one output result of a deep neural network. Embodiments may also include training the deep neural network with the global route data and the detail route data and predicting an output associated with a detail route based upon, at least in part, a trained deep neural network model.

Abstract: A method of generating a fixed-point type neural network by quantizing a floating-point type neural network, includes obtaining, by a device, a plurality of post-activation values by applying an activation function to a plurality of activation values that are received from a layer included in the floating-point type neural network, and deriving, by the device, a plurality of statistical characteristics for at least some of the plurality of post-activation values. The method further includes determining, by the device, a step size for the quantizing of the floating-point type neural network, based on the plurality of statistical characteristics, and determining, by the device, a final fraction length for the fixed-point type neural network, based on the step size.

Abstract: It is possible to improve estimation accuracy with regard to data in which significance is attached to a relative phase. Provided is an information processing device including an estimation unit configured to estimate a status by using a neural network. The neural network includes a first complex-valued neural network to which complex data is input, a phase difference computation layer from which phase difference for each element between a plurality of sets with regard to the complex data is output, and a second complex-valued neural network from which complex data is output on the basis of the phase difference.

Abstract: The technology disclosed proposes using a combination of computationally cheap, less-accurate bag of words (BoW) model and computationally expensive, more-accurate long short-term memory (LSTM) model to perform natural processing tasks such as sentiment analysis. The use of cheap, less-accurate BoW model is referred to herein as “skimming”. The use of expensive, more-accurate LSTM model is referred to herein as “reading”. The technology disclosed presents a probability-based guider (PBG). PBG combines the use of BoW model and the LSTM model. PBG uses a probability thresholding strategy to determine, based on the results of the BoW model, whether to invoke the LSTM model for reliably classifying a sentence as positive or negative. The technology disclosed also presents a deep neural network-based decision network (DDN) that is trained to learn the relationship between the BoW model and the LSTM model and to invoke only one of the two models.

Abstract: The present disclosure relates to a computer-implemented method for routing in an electronic design. Embodiments may include receiving, using at least one processor, global route data associated with an electronic design as an input and generating detail route data, based upon, at least in part, the global route data. Embodiments may further include transforming one or more of the detail route data and the global route data into at least one input feature and at least one output result of a deep neural network. Embodiments may also include training the deep neural network with the global route data and the detail route data and predicting an output associated with a detail route based upon, at least in part, a trained deep neural network model. Embodiments may also include generating routing information for each routing grid.

Abstract: A computer-implemented method and computing system are provided for failure prediction of a batch of manufactured objects. The method includes classifying, by a processor sing a simulation, a set of samples with uniformly distributed parameter values, to generate sample classifications for the batch of manufactured objects. The method further includes determining, by the processor, a centroid of failing ones of the samples in the set, based on the sample classifications. The method also includes generating, by the processor, a new set of samples with a distribution around the centroid of the failing ones of the sample in the set. The method additionally includes populating, by the processor, a nearest neighbor vector space using the new set of samples. The method further includes classifying, by the processor, the new set of samples by performing a nearest neighbor search on the nearest neighbor vector space using a distance metric.