Abstract: In some embodiments, a method includes storing data associated with fungible assets in a distributed ledger database. The method includes dividing fungible tokens into a first set of groups of fungible tokens based on the data and sending, via the distributed ledger-based network and based on an asymmetric cryptography key pair, each group of fungible tokens from the first set of groups of fungible tokens to a communication device from the first set of communication devices to cause the second plurality of communication devices to send, to a designated recipient communication device, non-fungible tokens for each group of fungible tokens from the second set of groups of fungible tokens. The first set of groups of fungible tokens is divided into a second set of groups of fungible tokens and received at a second set of communication devices.

Abstract: An apparatus includes a custodial mechanism that receive, from each compute device from at a quorum, an encrypted shard associated with a private key of a digital wallet and a cryptographic proof. The encrypted shard can be generated using an encryption key for the compute device. The cryptographic proof indicates that the compute device can decrypt the encrypted shard using a decryption key associated with that compute device and without revealing a value of the private key for the digital wallet. The apparatus generates, for each compute device, a cryptographic proof verification based on the encrypted shard for that compute device and an encryption witness for the private key of the digital wallet. The cryptographic proof verification indicates that the set of shards decrypted from the set of encrypted shards can be combined to reconstruct the private key.

Abstract: A multi-label ranking method includes receiving, at a processor and from a first set of artificial neural networks (ANNs), multiple signals representing a first set of ANN output pairs for a first label. A signal representing a second set of ANN output pairs for a second label different from the first label is received at the processor from a second set of ANNs different from the first set of ANNs, substantially concurrently with the first set of ANN output pairs. A first activation function is solved based on the first set of ANN output pairs, and a second activation function is solved based on the second set of ANN output pairs. Loss values are calculated based on the solved activations, and a mask is generated based on at least one ground truth label. A signal, including a representation of the mask, is sent from the processor to each of the sets of ANNs.

Abstract: Methods and apparatus for end-to-end unsupervised multi-document blind image denoising is presented. The multi-document blind image denoiser removes various noise types from noisy documents without paired target cleaned documents and preserves the contents for optical character recognition. The end-to-end unsupervised multi-document blind image denoiser integrates a Mixture of Experts with a cycle-consistent GAN as the base network that effectively removes multiple types of noise, including salt & pepper noise, blurred and/or faded text, as well as watermarks from documents at various levels of intensity.

Abstract: A method includes receiving, at a first compute device, a latent vector from a first machine learning model associated with a plurality of compute devices that includes the first compute device. The latent vector is provided as input to a second machine learning model to produce a predicted topic vector and a predicted cryptographic key. The predicted cryptographic key is compared to a cryptographic key to produce a first similarity metric value. The predicted topic vector is compared to a plurality to topic vectors of a database to produce a plurality of second similarity metric values. Embedded user data is received from a second compute device from the plurality of compute devices, and context data is sent from the database to the second compute device based on the embedded user data.

Abstract: In an embodiment, a transaction dataset is analyzed to identify a set of transaction events, each transaction event from the set of transaction events associated with a transaction event type. The set of transaction events is analyzed to identify a plurality of sets of grouped transaction events, each set of grouped transaction events from the plurality of sets of grouped transaction events associated with a subset of transaction events from the set of transaction events. To identify a plurality of sets of variants, each set of grouped transaction events from the plurality of sets of grouped transaction events including an identifier of a variant for that set of grouped transaction events and from the plurality of sets of variants is analyzed, each set of variants from the plurality of sets of variants differing from each remaining set of variants from the plurality of sets of variants.

Abstract: A method for converting a lineless table into a lined table includes associating a first set of tables with a second set of tables to form a set of multiple table pairs that includes tables with lines and tables without lines. A conditional generative adversarial network (cGAN) is trained, using the table pairs, to produce a trained cGAN. Using the trained cGAN, lines are identified for overlaying onto a lineless table. The lines are overlaid onto the lineless table to produce a lined table.

Abstract: A method according to an embodiment includes receiving, at one or more processors, (1) first data that is structured according to a first schema and that includes a first representation of an entity and (2) an indication of a target schema. The method also includes generating, using the one or more processors, an elemental specification associated with the first data. The method also includes generating, using the one or more processors and based on (1) the elemental specification and (2) a translation specification associated with the target schema, second data structured according to the target schema, the second data including a second representation of the entity that is equivalent to the first representation of the entity.

Abstract: A method for validating a current position of a first vehicle, the method comprising: receiving position data from the first vehicle, the position data providing the current position of the first vehicle; receiving position validation data associated with the first vehicle, the position validation data being generated by a source distinct from the first vehicle; and validating the current position of the first vehicle provided by the position data against the position validation data to determine an accuracy value for the current position.

Abstract: In some embodiments, a method includes storing data associated with fungible assets in a distributed ledger database. The method includes dividing fungible tokens into a first set of groups of fungible tokens based on the data and sending, via the distributed ledger-based network and based on an asymmetric cryptography key pair, each group of fungible tokens from the first set of groups of fungible tokens to a communication device from the first set of communication devices to cause the second plurality of communication devices to send, to a designated recipient communication device, non-fungible tokens for each group of fungible tokens from the second set of groups of fungible tokens. The first set of groups of fungible tokens is divided into a second set of groups of fungible tokens and received at a second set of communication devices.

Abstract: A node is provided that is configured to interact with one or more other nodes to implement a distributed authentication protocol. The node is configured to receive data that is indicative of use of a physical asset, generate a usage fee to be assigned to one or more owners of the physical asset in dependence on the use data and record that usage fee in a data corpus authenticated by the distributed authentication protocol.

Abstract: In some embodiments, a method includes storing data associated with fungible assets in a distributed ledger database. The method includes dividing fungible tokens into a first set of groups of fungible tokens based on the data and sending, via the distributed ledger-based network and based on an asymmetric cryptography key pair, each group of fungible tokens from the first set of groups of fungible tokens to a communication device from the first set of communication devices to cause the second plurality of communication devices to send, to a designated recipient communication device, non-fungible tokens for each group of fungible tokens from the second set of groups of fungible tokens. The first set of groups of fungible tokens is divided into a second set of groups of fungible tokens and received at a second set of communication devices.

Abstract: A method is described for validating a current position of a vehicle. The method includes receiving position data from the vehicle, receiving position validation data associated with the vehicle, and validating the current position of the vehicle provided by the position data against the position validation data to determine an accuracy value for the current position. The position data provides the current position of the vehicle, and the position validation data is generated by a source distinct from the vehicle.

Abstract: A method for validating a current position of a first vehicle, the method comprising: receiving position data from the first vehicle, the position data providing the current position of the first vehicle; receiving position validation data associated with the first vehicle, the position validation data being generated by a source distinct from the first vehicle; and validating the current position of the first vehicle provided by the position data against the position validation data to determine an accuracy value for the current position.

Abstract: One or more embodiments described herein disclose methods and systems that are directed at providing enhanced privacy, efficiency, convenience and security to distributed ledger-based networks (DLNs) via the implementation of zero-knowledge proofs (ZKPs) in the DLNs. ZKPs allow participants of DLNs to make statements on the DLNs about some private information and to prove the truth of the information without having to necessarily reveal the private information publicly. As such, the disclosed methods and systems directed at the ZKP-enabled DLNs provide privacy, ease and efficiency to participants of the DLNs while still allowing the DLNs to remain as consensus-based networks.

Abstract: Distributed ledger-based networks (DLNs) employ self-executing codes, also known as smart contracts, to manage interactions occurring on the networks, which may result in the generation of a massive amount of DLN state data representing the interactions and participants thereof. The instant disclosure discloses systems, apparatus and methods that allow interactions to occur on the DLNs without modification to stored data, thereby improving the storage capabilities of the networks.

Abstract: A processor-implemented method for the ownership transfer and tracking of tangible assets using a blockchain is described. In an embodiment, the method includes generating a root node associated with a tangible asset via a processor. The root node has a first hash value that represents a storage location of the root node, data associated with a tangible asset, and a second hash value that represents a storage location of the subsidiary node. The method also includes storing a hierarchical hash-linked tree structure in a non-transitory, processor-readable memory. The hierarchical hash-linked tree structure can include multiple nodes. The multiple nodes include the root node and the subsidiary node. The subsidiary node has the second hash value, and data associated with a tangible sub-asset of the tangible asset.

Abstract: In some embodiments, a method includes identifying a set of word bounding boxes in a first electronic document, and identifying locations of horizontal white space between two adjacent rows from a set of rows in a table. The method includes determining, using a Natural Language Processing algorithm, an entity name from a set of entity names for each table cell from a set of table cells in the table. The method includes determining, using a machine learning algorithm a class from a set of classes for each row from the set of rows. The method includes extracting a set of table cell values associated with the set of table cells, and generating a second electronic document including the set of table cell values arranged in the set of rows and the set of columns such that the set of words in the table are computer-readable in the second electronic document.

Abstract: In some embodiments, a method includes generating, based on distributed ledger data associated with a first distributed ledger-based network (DLN), distributed ledger data associated with a second DLN. The first DLN and the second DLN each is a fork and the distributed ledger data associated with the first DLN include account data associated with a set of accounts. The method includes generating a request to initiate a transaction between a first account and a second account. The method includes authenticating the transaction based on a protocol associated with the second DLN and without using a private cryptographic key of the first account. The method includes sending a signal indicating the transaction was authenticated and storing information associated with the transaction in the distributed ledger data associated with the second DLN.

Abstract: A node is provided for implementing an asset sharing scheme in which the asset is mobile. The node being is to determine a location of the mobile asset in dependence on data, relating to the mobile asset, that is recorded in a data corpus authenticated by a distributed authentication protocol. The node may be configured to interact with other nodes to implement the distributed authentication protocol.