Abstract: Tools for fire monitoring are presented. One method includes an operation for accessing values of features for monitoring a fire in a region. The features include satellite images at a first resolution, vegetation information, and weather data. Further, each satellite image includes first cells associated with the geographical region and the first resolution defines a first size of each first cell. The method further includes generating a map of the geographical region comprising a plurality of second cells having a second size, which is smaller than the first size. Additionally, the method includes operations for estimating, using a machine-learning model, probability values for the second cells in the map based on the features, each probability value indicating if the second cell contains an active fire, and for updating the map based on the probability values for the second cells. The map is presented in a user interface.

Abstract: Complex computer system architectures are described for utilizing a knowledge data graph comprised of elements, and selecting a discovery element to replace an existing element of a formulation depicted in the knowledge data graph. The substitution process takes advantage of the knowledge data graph structure to improve the computing capabilities of a computing device executing a substitution calculation by translating the knowledge data graph into an embedding space, and determining a discovery element from within the embedding space.

Abstract: Methods, systems, and computer programs are presented for tools for fire monitoring. One method includes an operation for receiving, by a fire forecasting program, fire-related inputs including vegetation data, topography data, weather data, and fire-monitoring information. The fire-monitoring information includes the shape of fire burning in a region. Additionally, the method includes an operation for generating a fire forecast for the region based on the fire-related inputs. The fire forecast describes a state of the fire in the region at multiple times in the future, the state of the fire comprising a fire perimeter, a fire line intensity, and a flame height. Additionally, the method includes operations for receiving updated fire-monitoring information regarding a current state of the fire in the region, for modifying the fire forecast based on the updated fire-monitoring information, and for causing presentation of the fire forecast in a user interface.

Abstract: Knowledge graph systems are disclosed for enhancing a knowledge graph by generating a new node. The knowledge graph system converts a knowledge graph into an embedding space, and selects a region of interest from within the embedding space. The knowledge graph system further identifies, from the region of interest, one or more gap regions, and calculates a center for each gap region. A node is generated for each gap region, and the information represented by the node is added to the original knowledge graph to generate an updated knowledge graph.

Abstract: This disclosure provides methods and systems for predicting missing links and previously unknown numerals in a knowledge graph. A jointly trained multi-task machine learning model is disclosed for integrating a symbolic pipeline for predicting missing links and a regression numerical pipeline for predicting numerals with prediction uncertainty. The two prediction pipelines share a jointly trained embedding space of entities and relationships of the knowledge graph. The numerical pipeline additionally includes a second-layer multi-task regression neural network containing multiple regression neural networks for parallel numerical prediction tasks with a cross stich network allowing for information/model parameter sharing between the various parallel numerical prediction tasks.

Abstract: The present disclosure relates to systems, methods, and products for identifying candidate molecule. The system includes a non-transitory memory storing instructions; and a processor in communication with the non-transitory memory. The processor executes the instructions to cause the system to receive drug data; convert the drug data into at least one point in a latent space using a grammar variational auto-encoder (VAE) model; receive a query for the at least one candidate molecule; select one or more points in the latent space; and create a k-dimensional tree graph based on the query for the at least one candidate molecule and the selected one or more points; determine a plurality of paths according to an interpolation technique; receive preference data; determine an optimum path; determine at least one candidate point on the optimum path; and determine a drug molecular structure using an inverse of the grammar VAE model.

Abstract: A device may generate a synthetic knowledge graph based on a true knowledge graph, may partition the synthetic knowledge graph into a set of synthetic data partitions, and may determine, using a plurality of teacher models, an aggregated prediction. The aggregated prediction may be based on individual predictions from corresponding individual teacher models included in the plurality of teacher models. The device may determine, using a student model and based on the synthetic knowledge graph and noise, a student prediction. The student model may be trained based on historical synthetic knowledge graphs and historical aggregated predictions associated with the plurality of teacher models. The device may determine an error metric based on the aggregated prediction and the student prediction, and may perform an action associated with the synthetic knowledge graph based on the error metric.

Abstract: A device processes a knowledge graph to select a set of triples and generates a first class based on the set of triples. The device determines a quantity of quasi-identifier attributes in the first class and compares the quantity to a predefined parameter. The device embeds the knowledge graph to generate an embedding space representation, identifies a second class, and determines a first quantity of nodes in the first class and the second class. The device compares the first quantity to the predefined parameter and identifies a third class. The device determines a second quantity of nodes in the first class and the third class and compares the second quantity to the predefined parameter. The device merges the second class or the third class with the first class, based on the comparisons, to generate anonymized nodes for the knowledge graph.

Abstract: In some implementations, a system may determine, based on a qualification model, a prediction output of an analysis of user information. The system may determine, based on a generator model, a plurality of counterfactual explanations associated with the prediction output and the user information. The system may cluster, according to a clustering model, the plurality of counterfactual explanations into clusters of counterfactual explanations. The system may select, based on a classification model, a counterfactual explanation from a cluster of the clusters of counterfactual explanations. The system may provide a request for feedback associated with the counterfactual explanation. The system may receive feedback data associated with the request for feedback. The system may update a data structure associated with the clustering model based on the feedback data and the counterfactual explanation to form an updated data structure. The system may perform an action associated with the updated data structure.

Abstract: Tools for fire monitoring are presented. One method includes an operation for accessing values of features for monitoring a fire in a region. The features include satellite images at a first resolution, vegetation information, and weather data. Further, each satellite image includes first cells associated with the geographical region and the first resolution defines a first size of each first cell. The method further includes generating a map of the geographical region comprising a plurality of second cells having a second size, which is smaller than the first size. Additionally, the method includes operations for estimating, using a machine-learning model, probability values for the second cells in the map based on the features, each probability value indicating if the second cell contains an active fire, and for updating the map based on the probability values for the second cells. The map is presented in a user interface.

Abstract: Tools for fire monitoring are presented. One method includes an operation for accessing values of features for monitoring a fire in a region. The features include satellite images at a first resolution, vegetation information, and weather data. Further, each satellite image includes first cells associated with the geographical region and the first resolution defines a first size of each first cell. The method further includes generating a map of the geographical region comprising a plurality of second cells having a second size, which is smaller than the first size. Additionally, the method includes operations for estimating, using a machine-learning model, probability values for the second cells in the map based on the features, each probability value indicating if the second cell contains an active fire, and for updating the map based on the probability values for the second cells. The map is presented in a user interface.

Abstract: A device may generate a synthetic knowledge graph based on a true knowledge graph, may partition the synthetic knowledge graph into a set of synthetic data partitions, and may determine, using a plurality of teacher models, an aggregated prediction. The aggregated prediction may be based on individual predictions from corresponding individual teacher models included in the plurality of teacher models. The device may determine, using a student model and based on the synthetic knowledge graph and noise, a student prediction. The student model may be trained based on historical synthetic knowledge graphs and historical aggregated predictions associated with the plurality of teacher models. The device may determine an error metric based on the aggregated prediction and the student prediction, and may perform an action associated with the synthetic knowledge graph based on the error metric.

Abstract: Methods, systems, and computer programs are presented for providing a user interface for fire management. One method includes an operation for estimating, by a fire management system, a fire state in a region and a forecast of an evolution of a fire at multiple times. The fire management program provides a user interface presenting fire information based on the estimated fire state and the forecast. The user interface includes a map of the region, a graphical representation of the fire information, and a time bar for selecting a time for the fire information. Additionally, the method includes an operation for receiving, via the user interface, a selection of the time for the fire information. The selected time is one of a past time, a present time, or a future time. The fire management program presents in the user interface the fire information for the selected time.

Abstract: The present disclosure relates to systems, methods, and products for identifying candidate molecule. The system includes a non-transitory memory storing instructions; and a processor in communication with the non-transitory memory. The processor executes the instructions to cause the system to receive drug data; convert the drug data into at least one point in a latent space using a grammar variational auto-encoder (VAE) model; receive a query for the at least one candidate molecule; select one or more points in the latent space; and create a k-dimensional tree graph based on the query for the at least one candidate molecule and the selected one or more points; determine a plurality of paths according to an interpolation technique; receive preference data; determine an optimum path; determine at least one candidate point on the optimum path; and determine a drug molecular structure using an inverse of the grammar VAE model.

Abstract: A process receives, with a processor, video content. Further, the process splices, with the processor, the video content into a plurality of video frames. In addition, the process splices, with the processor, at least one of the plurality of video frames into a plurality of image patches. Moreover, the process performs, with a neural network, an image reconstruction of at least one of the plurality of image patches to generate a reconstructed image patch. The process also compares, with the processor, the reconstructed image patch with the at least one of the plurality of image patches. Finally, the process determines, with the processor, a pixel error within the at least one of the plurality of image patches based on a discrepancy between the reconstructed image patch and the at least one of the plurality of image patches.

Abstract: This disclosure provides methods and systems for predicting missing links and previously unknown numerals in a knowledge graph. A jointly trained multi-task machine learning model is disclosed for integrating a symbolic pipeline for predicting missing links and a regression numerical pipeline for predicting numerals with prediction uncertainty. The two prediction pipelines share a jointly trained embedding space of entities and relationships of the knowledge graph. The numerical pipeline additionally includes a second-layer multi-task regression neural network containing multiple regression neural networks for parallel numerical prediction tasks with a cross stich network allowing for information/model parameter sharing between the various parallel numerical prediction tasks.

Abstract: The systems and methods described herein may generate multi-modal embeddings with sub-symbolic features and symbolic features. The sub-symbolic embeddings may be generated with computer vision processing. The symbolic features may include mathematical representations of image content, which are enriched with information from background knowledge sources. The system may aggregate the sub-symbolic and symbolic features using aggregation techniques such as concatenation, averaging, summing, and/or maxing. The multi-modal embeddings may be included in a multi-modal embedding model and trained via supervised learning. Once the multi-modal embeddings are trained, the system may generate inferences based on linear algebra operations involving the multi-modal embeddings that are relevant to an inference response to the natural language question and input image.

Abstract: The systems and methods described herein may generate multi-modal embeddings with sub-symbolic features and symbolic features. The sub-symbolic embeddings may be generated with computer vision processing. The symbolic features may include mathematical representations of image content, which are enriched with information from background knowledge sources. The system may aggregate the sub-symbolic and symbolic features using aggregation techniques such as concatenation, averaging, summing, and/or maxing. The multi-modal embeddings may be included in a multi-modal embedding model and trained via supervised learning. Once the multi-modal embeddings are trained, the system may generate inferences based on linear algebra operations involving the multi-modal embeddings that are relevant to an inference response to the natural language question and input image.

Abstract: The disclosure enables latent space exploration of a dataset based on drug molecular-structure data and drug biological-treatment data for a set of drug compounds in order to determine optimal drug compounds for treating diseases. Regional interpolation, including a linear interpolation (LERP) operation and a non-linear interpolation operation such as a spherical linear interpolation (SLERP), along with quantitative structure-activity relationship (QSAR) models may be utilized to navigate through a latent space generated from a variational auto-encoder (VAE), in accordance with certain embodiments.

Abstract: This disclosure relates to a development and application of a deep-learning neural network (DNN) model for identifying relevance of an information item returned by a search engine in response to a search query by a user, with respect to the search query and a profile for the user. The DNN model includes a set of neural networks arranged to learn correlations between queries, search results, and user profiles using dense numerical word or character embeddings and based on training targets derived from a historical search log containing queries, search results, and user-click data. The DNN model help identifying search results that are relevant to users according to their profiles.