Abstract: A product configuration device outputs a configuration of a product in accordance with a set of configuration rules. The product configuration device includes a rule learning system configured to acquire a first set of data representing a plurality of configurations of the product; to generate a neural network model representing the first set of data; to extract relationships between configuration attributes from the neural network model; and to modify the set of configuration rules based on the extracted relationships to generate a modified set of configuration rules for the product configuration device. The product configuration device may also include a rule execution engine that outputs the configuration of the product based on the modified set of configuration rules.

Abstract: A computer-implemented method for managing datasets of a storage system is provided, wherein the datasets have respective sets of metadata, the method including: successively feeding first sets of metadata to a spiking neural network (SNN), the first sets of metadata fed corresponding to datasets of the storage system that are labeled with respect to classes they belong to, so as to be associated with class labels, for the SNN to learn representations of said classes in terms of connection weights that weight the metadata fed; successively feeding second sets of metadata to the SNN, the second sets of metadata corresponding to unlabeled datasets of the storage system, for the SNN to infer class labels for the unlabeled datasets, based on the second sets of metadata fed and the representations learned; and managing datasets in the storage system, based on class labels of the datasets, these including the inferred class labels.

Abstract: An information processing apparatus includes: a memory configured to store program instructions to perform quantization on quantization target data; and a processor configured to execute the program instructions stored in the memory, the program instructions including: obtaining a distribution of appearance frequencies of a plurality of variable elements included in the quantization target data; and aligning a most significant bit position of a quantization position to a variable element smaller than a variable element of a maximum value among the plurality of variable elements based on the distribution of the appearance frequencies of the plurality of variable elements.

Abstract: An information processing device generates a prediction output corresponding to input data. The information processing device includes input-node specification processor circuitry, based on the input data, configured to specify input nodes corresponding to the input data and each located on a corresponding one of layers from beginning to end of the learning tree structured, reliability-index acquisition processor circuitry configured to acquire a reliability index obtained through the predetermined learning processing and indicating prediction accuracy, output-node specification processor circuitry, based on the reliability index acquired by the reliability-index acquisition processor circuitry configured to specify, from the input nodes corresponding to the input data, an output node that is the basis of the generation of a prediction output, and prediction-output generation processor circuitry configured to generate a prediction output.

Abstract: A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform obtaining a set of items that have been grouped together as matching items in a group; performing an ensemble mismatch detection; performing multiple detection models on the set of items to generate respective outputs regarding mismatches; combining the respective outputs to determine whether a quantity of detected mismatches is at least a predetermined threshold; when the quantity of detected mismatches is at least the predetermined threshold, the acts also can include separating at least one of the set of items from the group; and when the quantity of detected mismatches is not at least the predetermined threshold, the acts additionally can include maintaining each item of the set of items in the group. Other embodiments are disclosed.

Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices is described.

Abstract: An embodiment of the present disclosure provides a weight precision configuration method, including: determining a pre-trained preset neural network including a plurality of layers each having a preset weight precision; reducing, based on a current threshold, the weight precision of at least one layer in the preset neural network to obtain a corrected neural network having a recognition rate greater than the current threshold; and reducing the weight precision of a layer includes: adjusting the weight precision of the layer; setting, if a termination condition is met, the weight precision of the layer to a corrected weight precision that is less than or equal to the preset weight precision of the layer; and returning, if the termination condition is not met, to the operation of adjusting the weight precision of the layer; and determining a final weight precision of each layer to obtain a final neural network.

Abstract: The present disclosure provides systems and methods for synthetic data generation. A recurrent neural network can be trained for synthetic data generation by obtaining a sequence of elements and determining, using a classifier, that the sequence corresponds to a token. In response to the determination, a recurrent neural network configured to use a first vocabulary including the elements can be modified to use a second vocabulary, the second vocabulary including the token and the first vocabulary. The modified recurrent neural network can be trained using the token and the sequence of elements. The trained recurrent neural network can be used to generate synthetic data. A classifier can detect sequences of elements in the synthetic data corresponding to tokens. The tokens can replace the sequences of elements in the generated synthetic data and can be provided to the trained recurrent neural network to continue synthetic data generation.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network using normalized target outputs. One of the methods includes updating current values of the normalization parameters to account for the target output for the training item; determining a normalized target output for the training item by normalizing the target output for the training item in accordance with the updated normalization parameter values; processing the training item using the neural network to generate a normalized output for the training item in accordance with current values of main parameters of the neural network; determining an error for the training item using the normalized target output and the normalized output; and using the error to adjust the current values of the main parameters of the neural network.

Abstract: Systems and methods use deep, convolutional neural networks over exponentially long history windows to learn alphabets for context tree weighting (CTW) for prediction. Known issues of depth and breadth in conventional context tree weighting predictions are addressed by the systems and methods. To deal with depth, the history can be broken into time windows, permitting the ability to look exponentially far back while having less information the further one looks back. To deal with breadth, a deep neural network classifier can be used to learn to map arbitrary length histories to a small output symbol alphabet. The sequence of symbols produced by such a classifier over the history windows would then become the input sequence to CTW.

Abstract: Techniques for classifying heartbeats using patient electrocardiogram (ECG) data are described. ECG data is received, including waveform data and time interval data relating to a plurality of heartbeats for the patient. A convolutional neural network in a first path of a machine learning architecture generates a first plurality of output values by analyzing the waveform data. A fully-connected neural network in a second path of the machine learning architecture generates a second plurality of output values by analyzing the time interval data. The plurality of heartbeats in the ECG data are classified by concatenating the first plurality of output values and the second plurality of output values using the machine learning architecture.

Abstract: A method and an apparatus for optimizing and applying a multilayer neural network model, and a storage medium are provided. The optimization method includes, dividing out at least one sub-structure from the multilayer neural network model to be optimized, wherein a tail layer of the divided sub-structure is a quantization layer, and transferring operation parameters in layers other than the quantization layer to the quantization layer for each of the divided sub-structures and updating quantization threshold parameters in the quantization layer based on the transferred operation parameters. When a multilayer neural network model optimized based on the optimization method is operated, the necessary processor resources can be reduced.

Abstract: A machine receives a first set of global parameters from a global parameter server. The first set of global parameters includes data that weights one or more operands used in an algorithm that models an entity type. Multiple learner processors in the machine execute the algorithm using the first set of global parameters and a mini-batch of data known to describe the entity type. The machine generates a consolidated set of gradients that describes a direction for the first set of global parameters in order to improve an accuracy of the algorithm in modeling the entity type when using the first set of global parameters and the mini-batch of data. The machine transmits the consolidated set of gradients to the global parameter server. The machine then receives a second set of global parameters from the global parameter server, where the second set of global parameters is a modification of the first set of global parameters based on the consolidated set of gradients.

Abstract: Provided herein is an integrated circuit including, in some embodiments, a hybrid neural network including a plurality of analog layers, a digital layer, and a plurality of data outputs. The plurality of analog layers is configured to include programmed weights of the neural network for decision making by the neural network. The digital layer, disposed between the plurality of analog layers and the plurality of data outputs, is configured for programming to compensate for weight drifts in the programmed weights of the neural network, thereby maintaining integrity of the decision making by the neural network. Also provided herein is a method including, in some embodiments, programming the weights of the plurality of analog layers; determining the integrity of the decision making by the neural network; and programming the digital layer of the neural network to compensate for the weight drifts in the programmed weights of the neural network.

Abstract: Systems and methods for spatial graph convolutions in accordance with embodiments of the invention are illustrated. One embodiment includes a method for predicting characteristics for molecules, wherein the method includes performing a first set of graph convolutions with a spatial graph representation of a set of molecules, wherein the first set of graph convolutions are based on bonds between the set of molecules, performing a second set of graph convolutions with the spatial graph representation, wherein the second set of graph convolutions are based on at least a distance between each atom and other atoms of the set of molecules, performing a graph gather with the spatial graph representation to produce a feature vector, and predicting a set of one or more characteristics for the set of molecules based on the feature vector.

Abstract: According to the present disclosure, a weight parameter of a neural network is divided into a plurality of portions having a certain size and approximation is individually performed on the portions using a weighted sum of the codebook vectors.

Abstract: The present disclosure relates generally to an integrated machine learning platform. The machine learning platform can convert machine learning models with different schemas into machine learning models that share a common schema, organize the machine learning models into model groups based on certain criteria, and perform pre-deployment evaluation of the machine learning models. The machine learning models in a model group can be evaluated or used individually or as a group. The machine learning platform can be used to deploy a model group and a selector in a production environment, and the selector may learn to dynamically select the model(s) from the model group in the production environment in different contexts or for different input data, based on a score determined using certain scoring metrics, such as certain business goals.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for generating action recommendations for generating action recommendations for modifying physical emissions sources of an entity based on forecasting and monitoring emissions production for the entity utilizing machine-learning models. Specifically, the disclosed system forecasts emissions produced by an entity by utilizing a plurality of different forecasting machine-learning models corresponding to different physical emissions sources to generate forecasted source attributes. Additionally, the disclosed system combines the forecasted source attributes to generate a plurality of forecasted emissions value modifications for a future time period. The disclosed system generates action recommendations for modifying the physical emissions sources based on the forecasted emissions value modifications.

Abstract: Techniques for iterative query-based analysis of text are described. According to various implementations, a neural network architecture is implemented receives a query for information about text content, and iteratively analyzes the content using the query. During the analysis a state of the query evolves until it reaches a termination state, at which point the state of the query is output as an answer to the initial query.

Abstract: A system for informing food element decisions in the acquisition of edible materials from any source. The system includes a processor coupled to a memory configured to receive from a user client device a food element descriptor uniquely identifying a particular food element. The system retrieves from a physiological database at least an element of physiological data. The system identifies using at least an element of physiological data and a machine-learning algorithm user constitutional enhancing food elements and user constitutional advancing food elements. The system classifies using a food element classifier a food element descriptor. The system displays on a graphical user interface a constitutional enhancing food element or a constitutional advancing food element.