Abstract: An apparatus and method are described for distributed and cooperative computation in artificial neural networks. For example, one embodiment of an apparatus comprises: an input/output (I/O) interface; a plurality of processing units communicatively coupled to the I/O interface to receive data for input neurons and synaptic weights associated with each of the input neurons, each of the plurality of processing units to process at least a portion of the data for the input neurons and synaptic weights to generate partial results; and an interconnect communicatively coupling the plurality of processing units, each of the processing units to share the partial results with one or more other processing units over the interconnect, the other processing units using the partial results to generate additional partial results or final results. The processing units may share data including input neurons and weights over the shared input bus.

Abstract: A procedure for the global unified registration and universal identification of donors is described. The method includes a creation of one or more donor profiles, relevant medical data profiles, and a public common donor identifier from an initial registration. The procedure further includes identifying the donor by a donation center through a personal and non-transferable code for access to the data, the public common donor identifier and the stored profiles. The procedure automatically updates donor's data, profiles, and donation history in a database accessible by different donation centers.

Abstract: A procedure for the unified global registry and universal identification of products of biological origin for medicinal purposes is described. The method includes generation of a global and unique data storage vault for each product and related parties, one or more local data vaults associated with the global storage vault, one or more data profiles associated with the vaults, a unique and non-transferable public and private identifier associated with the global storage vault, one or more alphanumeric-hexadecimal translation maps associated with the public and private identifier, and a unique and non-transferable public identification code. The method further includes storing data in a database accessible by different parties depending on the data access rights. The method further includes identification of the data storage vault and the type of data stored through the unique and non-transferable identification code and automatically updating the information in the vaults and profiles stored in the database.

Abstract: An apparatus and method are described for distributed and cooperative computation in artificial neural networks. For example, one embodiment of an apparatus comprises: an input/output (I/O) interface; a plurality of processing units communicatively coupled to the I/O interface to receive data for input neurons and synaptic weights associated with each of the input neurons, each of the plurality of processing units to process at least a portion of the data for the input neurons and synaptic weights to generate partial results; and an interconnect communicatively coupling the plurality of processing units, each of the processing units to share the partial results with one or more other processing units over the interconnect, the other processing units using the partial results to generate additional partial results or final results. The processing units may share data including input neurons and weights over the shared input bus.

Abstract: A method of universal registration and identification of legal procedures and related parties and/or component parts to achieve the unification of the identification of legal procedures, allowing an individual or organization to carry the data related to their legal procedures, the verification of the related data, the assignation of access rights for accessing the data, as well as the unification of the history of procedures and documents. The generation of a unique and non-transferable public identifier for each legal procedure and also for each related part and it consists of different fields (some of the fields are mandatory and others are optional) combining URN, UUID, OID and DID formats. An entity such as an individual, an organization or a digital service can verify the authenticity of both the identifier of a legal procedure, of the DID document associated and of the data associated with said identifier.

Abstract: The present invention discloses a unified identification protocol for training and health, comprising: unified multipurpose identifier that serves to identify individuals and the relationships established with these individuals, such as relationships with entities, professionals, products, services and transactions, generation of a multipurpose identifier, unique, non-transferable and univocally distinguishable through a computer system. The computer system that identifies them universally to avoid identification errors, based on UUID, DID and/or other formats and unify the data of the same individual existing in different systems, stored in one or several electronic devices of the individual and/or their legal guardians and, additionally, in one or more cloud services, certify access permissions granted/revoked to the different data compartments in the profile of the individual and the authenticity of the data, carried out in one or more distributed data ledger technologies or blockchains.

Abstract: An apparatus and method are described for distributed and cooperative computation in artificial neural networks. For example, one embodiment of an apparatus comprises: an input/output (I/O) interface; a plurality of processing units communicatively coupled to the I/O interface to receive data for input neurons and synaptic weights associated with each of the input neurons, each of the plurality of processing units to process at least a portion of the data for the input neurons and synaptic weights to generate partial results; and an interconnect communicatively coupling the plurality of processing units, each of the processing units to share the partial results with one or more other processing units over the interconnect, the other processing units using the partial results to generate additional partial results or final results. The processing units may share data including input neurons and weights over the shared input bus.

Abstract: A processing device includes a processor core and a number of calculation modules that each is configurable to perform any one of operations for a convolutional neuron network system. A first set of the calculation modules are configured to perform convolution operations, a second set of the calculation modules are reconfigured to perform averaging operations, and a third set of the calculation modules are reconfigured to perform dot product operations.

Abstract: An apparatus and method are described for distributed and cooperative computation in artificial neural networks. For example, one embodiment of an apparatus comprises: an input/output (I/O) interface; a plurality of processing units communicatively coupled to the I/O interface to receive data for input neurons and synaptic weights associated with each of the input neurons, each of the plurality of processing units to process at least a portion of the data for the input neurons and synaptic weights to generate partial results; and an interconnect communicatively coupling the plurality of processing units, each of the processing units to share the partial results with one or more other processing units over the interconnect, the other processing units using the partial results to generate additional partial results or final results. The processing units may share data including input neurons and weights over the shared input bus.

Abstract: Continuous charcoal production system in a vertical reactor with a concentric charging zone (1) and drying zone (2), a carbonization zone (3), a cooling zone (4) and a discharge zone (5), and a method for recovering energy from carbonization gases for the production of this charcoal, comprising the extraction of carbonization gas from the drying zone (2) and subdividing it into recirculating gas and heating gas, with the remaining gas exceeding the energy required to generate electricity; burning the heating gas in a hot gas generator (11); injecting the recirculating gas into a heat recovery unit (9); injecting the heating gas after combustion into the heat recovery unit (9), indirect heating of the recirculating gas; and reinjecting the heated recirculating gas into the carbonization zone (3) of the reactor (R).

Abstract: A method of universal registration and identification of legal procedures and related parties and/or component parts to achieve the unification of the identification of legal procedures, allowing an individual or organization to carry the data related to their legal procedures, the verification of the related data, the assignation of access rights for accessing the data, as well as the unification of the history of procedures and documents. The generation of a unique and non-transferable public identifier for each legal procedure and also for each related part and it consists of different fields (some of the fields are mandatory and others are optional) combining URN, UUID, OID and DID formats. An entity such as an individual, an organization or a digital service can verify the authenticity of both the identifier of a legal procedure, of the DID document associated and of the data associated with said identifier.

Abstract: A procedure for the unified global registry and universal identification of products of biological origin for medicinal purposes is described. The method includes generation of a global and unique data storage vault for each product and related parties, one or more local data vaults associated with the global storage vault, one or more data profiles associated with the vaults, a unique and non-transferable public and private identifier associated with the global storage vault, one or more alphanumeric-hexadecimal translation maps associated with the public and private identifier, and a unique and non-transferable public identification code. The method further includes storing data in a database accessible by different parties depending on the data access rights. The method further includes identification of the data storage vault and the type of data stored through the unique and non-transferable identification code and automatically updating the information in the vaults and profiles stored in the database.

Abstract: A procedure for the global unified registration and universal identification of donors is described. The method includes a creation of one or more donor profiles, relevant medical data profiles, and a public common donor identifier from an initial registration. The procedure further includes identifying the donor by a donation center through a personal and non-transferable code for access to the data, the public common donor identifier and the stored profiles. The procedure automatically updates donor's data, profiles, and donation history in a database accessible by different donation centers.

Abstract: An apparatus and method are described for distributed and cooperative computation in artificial neural networks. For example, one embodiment of an apparatus comprises: an input/output (I/O) interface; a plurality of processing units communicatively coupled to the I/O interface to receive data for input neurons and synaptic weights associated with each of the input neurons, each of the plurality of processing units to process at least a portion of the data for the input neurons and synaptic weights to generate partial results; and an interconnect communicatively coupling the plurality of processing units, each of the processing units to share the partial results with one or more other processing units over the interconnect, the other processing units using the partial results to generate additional partial results or final results. The processing units may share data including input neurons and weights over the shared input bus.

Abstract: A procedure of unified registration and universal identification in any territory of spatially locatable objects, in order to achieve interoperability between objects or spatial locations, different types of computing systems, the procedure comprising: generation of a unique and non-transferable identifier for each connected, smart and spatial object device, in the URN UUID, OID and DID formats, without discarding others; creation of a DID document associated with the generated identifier; association of different identifiers of the object and of the user/owner; assignment of permissions, roles and creation of access control list (ACL); creation of encryption keys associated with the ACL; save in the DID document both data, service identifiers and other associated identifiers, as well as necessary permissions for accessing to object data; digital fingerprint generation of the DID document using hash; associated data and hash storage in the system and in one or more DLTs or blockchain networks.

Abstract: Continuous charcoal production system in a vertical reactor with a concentric charging zone (1) and drying zone (2), a carbonization zone (3), a cooling zone (4) and a discharge zone (5), and a method for recovering energy from carbonization gases for the production of this charcoal, comprising the extraction of carbonization gas from the drying zone (2) and subdividing it into recirculating gas and heating gas, with the remaining gas exceeding the energy required to generate electricity; burning the heating gas in a hot gas generator (11); injecting the recirculating gas into a heat recovery unit (9); injecting the heating gas after combustion into the heat recovery unit (9), indirect heating of the recirculating gas; and reinjecting the heated recirculating gas into the carbonization zone (3) of the reactor (R).

Abstract: The present invention discloses a unified identification protocol for training and health, comprising: unified multipurpose identifier that serves to identify individuals and the relationships established with these individuals, such as relationships with entities, professionals, products, services and transactions, generation of a multipurpose identifier, unique, non-transferable and univocally distinguishable through a computer system. The computer system that identifies them universally to avoid identification errors, based on UUID, DID and/or other formats and unify the data of the same individual existing in different systems, stored in one or several electronic devices of the individual and/or their legal guardians and, additionally, in one or more cloud services, certify access permissions granted /revoked to the different data compartments in the profile of the individual and the authenticity of the data, carried out in one or more distributed data ledger technologies or blockchains.

Abstract: A procedure for the unified global registry and universal identification of products of biological origin for medicinal purposes comprises: Generation of a global and unique data storage vault in the system for each product and related parties, one or more local data vaults associated with the global storage vault, one or more data profiles associated with the vaults, a unique and non-transferable public and private identifier associated with the global storage vault, one or more alphanumeric-hexadecimal translation maps associated with the public and private identifier, and a unique and non-transferable public identification code, and store these data in a database accessible by different parties depending on the data access rights. Identification of the data storage vault and the type of data stored through the unique and non-transferable identification code and automatic updating the information in the vaults and profiles stored in the database accessible by different parties.

Abstract: Systems, methods, and apparatuses for decomposing a sequential program into multiple threads, executing these threads, and reconstructing the sequential execution of the threads are described. A plurality of data cache units (DCUs) store locally retired instructions of speculatively executed threads. A merging level cache (MLC) merges data from the lines of the DCUs. An inter-core memory coherency module (ICMC) globally retires instructions of the speculatively executed threads in the MLC.

Abstract: Systems and methods for performing convolution operations. An example processing system comprises: a processing core; and a convolver unit to apply a convolution filter to a plurality of input data elements represented by a two-dimensional array, the convolver unit comprising a plurality of multipliers coupled to two or more sets of latches, wherein each set of latches is to store a plurality of data elements of a respective one-dimensional section of the two-dimensional array.