Abstract: Methods, systems, and computer-readable storage media for receiving, by an aromatic simulation platform, a recipe including descriptions indicative of ingredients of a consumable, processing the recipe through a first neural network to provide a recipe embedding, processing an ingredients profile to determine an aroma compounds profile representing the ingredients of the ingredients profile, processing the aroma compounds profile through a second neural network to provide an aroma embedding, and processing the recipe embedding and the aroma embedding through a third neural network to provide an aroma profile representative of the consumable of the recipe.

Abstract: A computer-implemented method comprising: obtaining, by way of an input, input data relating to speech provided by a user; deriving one or more hypotheses for each of a plurality of user data fields from the input data; obtaining one or more reference values for each of the plurality of user data fields for each of one or more candidate users; calculating a score for at least one candidate user of the one or more candidate users, calculating the score comprising: calculating a plurality of user data field scores comprising, for each of the plurality of user data fields, a respective user data field score using the one or more hypotheses and the one or more reference values for the candidate user for the respective user data field; performing one or more fuzzy logic operations on the plurality of user data field scores; using the score for a candidate user of the one or more candidate users to perform a verification or identification process for the user.

Abstract: Techniques that facilitate machine learning optimization are provided. In one example, a system includes a computational resource component, a batch interval component, and a machine learning component. The computational resource component collects computational resource data associated with a group of computing devices that performs a machine learning process. The batch interval component determines, based on the computational resource data, batch interval data indicative of a time interval to collect data for the machine learning process. The machine learning component provides the batch interval data to the group of computing devices to facilitate execution of the machine learning process based on the batch interval data.

Abstract: A computer-implemented method for learning structural relationships between nodes of a graph includes generating a knowledge graph comprising nodes representing a system and applying a graph-based convolutional neural network (GCNN) to the knowledge graph to generate feature vectors describing structural relationships between the nodes. The GCNN comprises: (i) a graph feature compression layer configured to learn subgraphs representing embeddings of the nodes of the knowledge graph into a vector space, (ii) a neighbor nodes aggregation layer configured to derive neighbor node feature vectors for each subgraph and aggregate the neighbor node feature vectors with their corresponding subgraphs to yield aggregated subgraphs, and (iii) a subgraph convolution layer configured to generate the feature vectors based on the aggregated subgraphs. Functional groups of components included in the system may then be identified based on the plurality of feature vectors.

Abstract: A method is used in analyzing a storage system using a machine learning system. Data gathered from information associated with operations performed in a storage system is analyzed. The storage system is comprised of a plurality of components. A bitmap image is created based on the gathered data, where at least one of the plurality of components is represented in the bitmap image. The machine learning system is trained using the bitmap image, where the bitmap image is organized to depict the plurality of components of the storage system.

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: 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: 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: 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: 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: 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.

Abstract: A system that provides a mathematical formulation for new problem of model validation and model selection in presence of test data feedback. The system comprises a memory that stores computer-executable components. A processor, operably coupled to the memory, executes the computer-executable components stored in the memory. A selection component selects a metric of performance evaluation accuracy; and a configuration component configures performance evaluation schemes for machine learning algorithms. A characterization component employs a supervised learning-based approach to characterize relationship between the configuration of the performance evaluation scheme and fidelity of performance estimates; and an optimization component that optimizes accuracy of the machine learning algorithms as a function of size of training data set relative to size of validation data set through selection of values associated with the configuration parameters.

Abstract: A system analyzes periodically collected data associated with entities, for example, users, servers, or systems. The system determines anomalies associated with populations of entities. The system excludes anomalies from consideration to increase efficiency of execution. The system may rank the anomalies based on relevance scores. The system determines relevance scores based on various factors describing the sets of entities. The system may present information describing the anomalies based on the ranking. The system may use a machine learning based model for predicting likelihoods of outcomes associated with sets of entities. The system generates alerts for reporting the outcomes based on the predictions.

Abstract: The present disclosure provides computing systems and techniques for validating a decision model against a cannon of regulation. A server can deconstruct a decision model into a number of branching decisions and also generate a Markov chain comprising a number of sequences from a cannon of regulation. The server can compare the branching decisions to the sequences and can validate the decision model with the cannon of regulation based on the comparison.