Abstract: A method for ranking genealogical records includes using a machine learning model to rank multiple searched records based on relevancy. The relevancy may be determined by identifying features included in a record and scaling each feature by a corresponding weight factor. In addition, a method for training a machine learning model and increasing the convergence speed of the training is described. To train the model, a machine learning process is used to optimize a ranking performance metric. A set of weights corresponding to multiple features are used to rank multiple past search records in a training set. An initial set of the weights are set by the expectation values of the weights. The weights are incrementally changed to optimize the ranking performance metric. The step size of the increment is determined based on the sensitivity of the ranking performance metric relative to the step size.

Abstract: Techniques for training a machine-learning (ML) model for captioning images are disclosed. A plurality of feature vectors and a plurality of visual attention maps are generated by a visual model of the ML model based on an input image. Each of the plurality of feature vectors correspond to different regions of the input image. A plurality of caption attention maps are generated by an attention model of the ML model based on the plurality of feature vectors. An attention penalty is calculcated based on a comparison between the caption attention maps and the visual attention maps. A loss function is calculcated based on the attention penalty. One or both of the visual model and the attention model are trained using the loss function.

Abstract: Systems and methods for registering documents. A two-dimensional document image and one or more form images may be obtained. The document image may be projected onto a horizontal axis and a vertical axis to create a horizontal document projection and a vertical document projection. The form images may be projected onto the horizontal axis and the vertical axis to create a horizontal form projection and a vertical form projection. The horizontal document projection may be correlated with the horizontal form projection of the form images and the vertical document projection may be correlated with the vertical form projection of the form images. Correlation scores may be calculated based on the correlations.

Abstract: Embodiments described herein relate generally to a methodology of efficient object classification within a visual medium. The methodology utilizes a first neural network to perform an attention based object localization within a visual medium to generate a visual mask. The visual mask is applied to the visual medium to generate a masked visual medium. The masked visual medium may be then fed into a second neural network to detect and classify objects within the visual medium.

Abstract: An input sample SNP genotype is divided into a plurality of windows, each including a sequence of SNPs. For each window, a diploid hidden Markov Model (HMM) is built and from a haplotype Markov Model (MM). The diploid HMM for a window is used to determine the probability that the window corresponds to a pair of labels (e.g., ethnicity labels). An inter-window HMM, with a set of states for each window, is built based on the diploid HMMs for each window. Labels are assigned to the input sample genotype based on the inter-window HMM.

Abstract: Systems and methods for retrieving a set of ordered items from a distributed database. A plurality of ordered items may be stored at a cache. The plurality of ordered items may have a length of N+B at a first instant in time. A first instruction to delete a first item of the plurality of ordered items may be received. A second instruction to add a second item to the plurality of ordered items may be received. The first instruction and the second instruction may be stored in a change log. A request for the first N items of the plurality of ordered items may be received. The first instruction may be executed by deleting the first item from the plurality of ordered items. The second instruction may be executed by adding the second item to the plurality of ordered items. The first N items of the plurality of ordered items may be sent in response to the request.

Abstract: Described are computational methods to reconstruct the chromosomes (and genomes) of ancestors given genetic data, IBD information, and full or partial pedigree information of some number of their descendants.

Abstract: Systems and methods for training a machine learning (ML) ranking model to rank genealogy hints are described herein. One method includes retrieving a plurality of genealogy hints for a target person, where each of the plurality of genealogy hints corresponds to a genealogy item and has a hint type of a plurality of hint types. The method includes generating, for each of the plurality of genealogy hints, a feature vector having a plurality of feature values, the feature vector being included in a plurality of feature vectors. The method includes extending each of the plurality of feature vectors by at least one additional feature value based on the number of features of one or more other hint types of the plurality of hint types. The method includes training the ML ranking model using the extended plurality of feature vectors and user-provided labels.

Abstract: Systems and methods for classifying historical images. A feature extractor may create feature vectors corresponding to a plurality of images. A first classification of the plurality of images may be performed based on the plurality of feature vectors, which may include assigning a label to each of the plurality of images and assigning a probability for each of the assigned labels. The assigned probability for each of the assigned labels may be related to a statistical confidence that a particular assigned label is correctly assigned to a particular image. A subset of the plurality of images may be displayed to a display device. An input corresponding to replacement of an incorrect label with a corrected label for a certain image may be received from a user. A second classification of the plurality of images based on the input from the user may be performed.

Abstract: Systems and methods for classifying historical images. A feature extractor may create feature vectors corresponding to a plurality of images. A first classification of the plurality of images may be performed based on the plurality of feature vectors, which may include assigning a label to each of the plurality of images and assigning a probability for each of the assigned labels. The assigned probability for each of the assigned labels may be related to a statistical confidence that a particular assigned label is correctly assigned to a particular image. A subset of the plurality of images may be displayed to a display device. An input corresponding to replacement of an incorrect label with a corrected label for a certain image may be received from a user. A second classification of the plurality of images based on the input from the user may be performed.

Abstract: Described embodiments enable identification of family networks using combinations of DNA analysis and genealogical information. Genealogical data is provided by users of a genealogical research service or collected from other sources and used to create family trees for each user. DNA samples are also received from the users. By analyzing the DNA samples, potential genetic relationships can be identified between some users. Once these DNA-suggested relationships have been identified, common ancestors can be sought in the respective trees of the potentially related users. Where these common ancestors exist, an inference is drawn that the DNA-suggested relationship accurately represents a familial overlap between the individuals in question. People descended from the same common ancestor are each members of a family network. Members of a family network not in a user's tree may be identified for the user, enabling the user to discover additional ancestors that might otherwise have remained unknown.

Abstract: A data record management system develops person match scores for data records that may relate to the same person or subject. In a genealogical system where the data records are represented as nodes in a family tree, and where multiple data records may relate the same person in question, the data record management system evaluates not only two data records to determine if they relate to the same person, but also individually evaluate various data records pertaining to people that are related to the person in question. Person match scores are calculated by combining sub-scores based on the comparison of corresponding nodes. Sub-scores for nodes pertaining to related people may be adjusted higher even if those notes do not match, to reflect circumstances such as remarriage.

Abstract: Described are techniques for determining population structure from identity-by-descent (IBD) of individuals. The techniques may be used to predict that an individual belongs to zero, one or more of a number of communities identified within an IBD network. Additional data may be used to annotate the communities with birth location, surname, and ethnicity information. In turn, these data may be used to provide to an individual a prediction of membership to zero, one or more communities, accompanied by a summary of the information annotated to those communities.

Abstract: A data record management system develops person match scores for data records that may relate to the same person or subject. In a genealogical system where the data records are represented as nodes in a family tree, and where multiple data records may relate the same person in question, the data record management system evaluates not only two data records to determine if they relate to the same person, but also individually evaluate various data records pertaining to people that are related to the person in question. Person match scores are calculated by combining sub-scores based on the comparison of corresponding nodes. Sub-scores for nodes pertaining to related people may be adjusted higher even if those notes do not match, to reflect circumstances such as remarriage.

Abstract: Identification of inheritance-by-descent haplotype matches between individuals is described. A set of tables including word match, haplotypes and segment match tables are populated. DNA samples are received and stored. A word identification module extracts haplotype values from each sample. The word match table is indexed according to the unique combination of position and haplotype. Each column represents a different sample, and each cell indicates whether that sample includes that haplotype at that position. The haplotypes table includes the raw haplotype data for each sample. The segment match table is indexed by sample identifier, and columns represent other samples. Each cell is populated to indicate for each identified sample pair which position range(s) include matching haplotypes for both samples. The tables are persistently stored in databases of the matching system. As new sample data is received, each table is updated to include the newly received samples, and additional matching takes place.

Abstract: Systems and methods for retrieving a set of ordered items from a distributed database. A plurality of ordered items may be stored at a cache. The plurality of ordered items may have a length of N+B at a first instant in time. A first instruction to delete a first item of the plurality of ordered items may be received. A second instruction to add a second item to the plurality of ordered items may be received. The first instruction and the second instruction may be stored in a change log. A request for the first N items of the plurality of ordered items may be received. The first instruction may be executed by deleting the first item from the plurality of ordered items. The second instruction may be executed by adding the second item to the plurality of ordered items. The first N items of the plurality of ordered items may be sent in response to the request.

Abstract: Methods and systems for creating a cluster view person for genealogical studies. Methods may include obtaining a plurality of genealogical trees. Each of the genealogical trees may include a plurality of interconnected nodes representing individuals that are related to each other. Methods may also include identifying one or more of the genealogical trees that contain a similar individual. Whether two individuals are grouped may depend on similarity and/or quality thresholds. Methods may include creating an aggregate individual including each of the similar individuals in each of the identified genealogical trees. The aggregate individual may combine information from each of the similar individuals.

Abstract: Systems and methods for registering documents. A two-dimensional document image and one or more form images may be obtained. The document image may be projected onto a horizontal axis and a vertical axis to create a horizontal document projection and a vertical document projection. The form images may be projected onto the horizontal axis and the vertical axis to create a horizontal form projection and a vertical form projection. The horizontal document projection may be correlated with the horizontal form projection of the form images and the vertical document projection may be correlated with the vertical form projection of the form images. Correlation scores may be calculated based on the correlations.