METHOD, MACHINE-READABLE MEDIUM AND SYSTEM TO PARAMETERIZE SEMANTIC CONCEPTS IN A MULTI-DIMENSIONAL VECTOR SPACE AND TO PERFORM CLASSIFICATION, PREDICTIVE, AND OTHER MACHINE LEARNING AND AI ALGORITHMS THEREON

1 - 25 . (canceled)

26 . A computer-implemented method of generating a training model to be used by a neural network-based computing system to process a data set regarding a plurality of semantic concepts, the method including:

performing a set of parameterizations of the plurality of semantic concepts, each parameterization of the set including:

receiving existing data on the plurality of semantic concepts at an input of a computer system, the computer system including memory circuitry and a processing circuitry coupled to the memory circuitry;

generating a data structure using the processing circuitry, the data structure corresponding to a Distributed Knowledge Graph (DKG) defined by a plurality of nodes each representing a respective one of the plurality of semantic concepts, the plurality of semantic concepts being based at least in part on the existing data, each of the nodes represented by a characteristic distributed pattern of activity levels for respective meta-semantic nodes (MSNs), the MSNs for said each of the nodes defining a standard basis vector to designate a semantic concept, wherein standard basis vectors for respective ones of the nodes together define a continuous vector space of the DKG; and

storing the data structure in the memory circuitry; and

in response to a determination that an error rate from a processing of the data set by the neural network-based computing system is above a predetermined threshold, performing a subsequent parameterization of the set, and otherwise generating the training model corresponding to the data structure from a last one of the set of parameterizations, the training model to be used by the neural network-based computing system to process further data sets.

27 . The computer-implemented method of claim 26 , wherein each MSN corresponds to an intersection of a plurality of dimensions, each activity level in the pattern of activity levels designating a value for a dimension of the plurality of dimensions.

28 . The computer-implemented method of claim 27 , further including determining a number of the plurality of dimensions prior to performing the set of parameterizations, wherein the number of the plurality of dimensions is to remain fixed after being determined.

29 . The computer-implemented method of claim 27 , wherein the plurality of dimensions includes a dimension representing a trajectory between a semantic concept and one of a prior semantic concept or a subsequent semantic concept in a string of semantic concepts, the method further including incrementing an activity level for the dimension representing the trajectory each time the processing circuitry identifies a string of semantic concepts that invokes the trajectory.

30 . The computer-implemented method of claim 27 , further including, after storing the data structure, superimposing data from an additional dimension to the vector space to reconfigure the vector space.

31 . The computer-implemented method of claim 30 , wherein superimposing includes superimposing data from an additional dimension to at least one of reconfigure dense regions of the vector space to facilitate a discrimination between closely related semantic concepts, or condense sparse regions of the vector space to facilitate a processing of the data structure.

32 . The computer-implemented method of claim 27 , wherein the method includes:

in response to a determination that the existing data includes a string of semantic concepts, after storing the data structure, superimposing data from an additional dimension to the vector space to reconfigure the vector space, the additional dimension including a dimension representing a trajectory between a semantic concept and one of a prior semantic concept or a subsequent semantic concept in a string of semantic concepts; and

incrementing an activity level for the dimension representing the trajectory each time the processing circuitry identifies a string of semantic concepts that invokes the trajectory.

33 . The computer-implemented method of claim 27 , wherein a dimension of the plurality of dimensions corresponds to a time dimension, and wherein an activity level for the time dimension represents one of time from a linear lunar calendar, time related to an event, time related to a linear scale, time related to a log scale, a non-uniform time scale, or cyclical time.

34 . The computer-implemented method of claim 27 , wherein a dimension of the plurality of dimensions corresponds to a space dimension, and wherein an activity level for the space dimension represents one of linear scaled latitude, linear scaled longitude, linear scale altitude, building coordinate codes, allocentric polar coordinates, Global Positioning System (GPS) coordinates, or indoor location WiFi based coordinates.

35 . The computer-implemented method of claim 26 , wherein a degree of similarity between semantic concepts is based on a feature between nodes corresponding thereto in the vector space, the feature including at least one of distance, manifold shapes and trajectories in the vector space.

36 . The computer-implemented method of claim 26 , wherein the neural network-based computing system is coupled to the memory circuitry, the method comprising using the neural network-based computing system to:

access the training model in the memory circuitry; and

process the data set based on the training model to generate a processed data set.

37 . The computer-implemented method of claim 36 , further including using the processed data set as part of the existing data set to perform a subsequent parameterization.

38 . The computer-implemented method of claim 36 , wherein using the neural network-based computing system to process the data set includes using the data set and the training model to determine at least one of: a most efficient trajectory from one of the nodes to another one of the nodes, nodes located close to a trajectory, a density of trajectories through a node, most likely next nodes, or most likely antecedents to a current node.

39 . The computer-implemented method of claim 36 , wherein the neural network-based computing system includes a plurality of neural network-based computing systems each coupled to the memory circuitry, the method including operating the neural network-based computing systems in parallel with one another to simultaneously process the data set based on respective dimensions or respective clusters of dimensions of data of the data set.

40 . A neural-network-based computer system including a memory circuitry and processing circuitry coupled to the memory circuitry, the memory circuitry loaded with instructions, the instructions, when executed by the processing circuitry, to cause the processing circuitry to perform operations comprising:

performing a set of parameterizations of a plurality of semantic concepts, each parameterization of the set including:

receiving existing data on the plurality of semantic concepts;

generating a data structure corresponding to a Distributed Knowledge Graph (DKG) defined by a plurality of nodes each representing a respective one of the plurality of semantic concepts, the plurality of semantic concepts being based at least in part on the existing data, each of the nodes represented by a characteristic distributed pattern of activity levels for respective meta-semantic nodes (MSNs), the MSNs for said each of the nodes defining a standard basis vector to designate a semantic concept, wherein standard basis vectors for respective ones of the nodes together define a continuous vector space of the DKG; and

storing the data structure in the memory circuitry; and

in response to a determination that an error rate from a processing of a data set by the neural network-based computing system is above a predetermined threshold, performing a subsequent parameterization of the set, and otherwise generating a training model corresponding to the data structure from a last one of the set of parameterizations, the training model to be used by the neural network-based computing system to process further data sets.

41 . The computer system of claim 40 , wherein each MSN corresponds to an intersection of a plurality of dimensions, each activity level in the pattern of activity levels designating a value for a dimension of the plurality of dimensions.

42 . The computer system of claim 41 , wherein the plurality of dimensions includes a dimension representing a trajectory between a semantic concept and one of a prior semantic concept or a subsequent semantic concept in a string of semantic concepts, the operations further including incrementing an activity level for the dimension representing the trajectory each time the processing circuitry identifies a string of semantic concepts that invokes the trajectory.

43 . The computer system of claim 41 , the operations further including, after storing the data structure, superimposing data from an additional dimension to the vector space to reconfigure the vector space.

44 . The computer system of claim 41 , wherein the operations include:

in response to a determination that the existing data includes a string of semantic concepts, after storing the data structure, superimposing data from an additional dimension to the vector space to reconfigure the vector space, the additional dimension including a dimension representing a trajectory between a semantic concept and one of a prior semantic concept or a subsequent semantic concept in a string of semantic concepts; and

incrementing an activity level for the dimension representing the trajectory each time the processing circuitry identifies a string of semantic concepts that invokes the trajectory.

45 . The computer system of claim 40 , wherein the computer system includes the neural network-based computing system, the neural network-based computing system coupled to the memory circuitry and adapted to:

access the training model in the memory circuitry; and

process the data set based on the training model to generate a processed data set.

46 . The computer system of claim 45 , wherein the neural network-based computing system is to use the data set and the training model to determine at least one of: a most efficient trajectory from one of the nodes to another one of the nodes, nodes located close to a trajectory, a density of trajectories through a node, most likely next nodes, or most likely antecedents to a current node.

47 . The computer system of claim 45 , wherein the neural network-based computing system includes a plurality of neural network-based computing systems each coupled to the memory circuitry, the neural network-based computing systems to operate in parallel with one another to simultaneously process the data set based on respective dimensions or respective clusters of dimensions of data of the data set.

48 . A product comprising one or more tangible computer-readable non-transitory storage media comprising computer-executable instructions operable to, when executed by at least one computer processor of a neural network-based computing system, enable the at least one processor to:

perform a set of parameterizations of a plurality of semantic concepts, each parameterization of the set including:

receiving existing data on the plurality of semantic concepts;

generating a data structure corresponding to a Distributed Knowledge Graph (DKG) defined by a plurality of nodes each representing a respective one of the plurality of semantic concepts, the plurality of semantic concepts being based at least in part on the existing data, each of the nodes represented by a characteristic distributed pattern of activity levels for respective meta-semantic nodes (MSNs), the MSNs for said each of the nodes defining a standard basis vector to designate a semantic concept, wherein standard basis vectors for respective ones of the nodes together define a continuous vector space of the DKG; and

storing the data structure;

in response to a determination that an error rate from a processing of the data set by the neural network-based computing system is above a predetermined threshold, perform a subsequent parameterization of the set; and

in response to a determination that an error rate from a processing of the data set by the neural network-based computing system is below a predetermined threshold, generate a training model corresponding to the data structure from a last one of the set of parameterizations, the training model to be used by the neural network-based computing system to process further data sets.

49 . The product of claim 48 , wherein each MSN corresponds to an intersection of a plurality of dimensions, each activity level in the pattern of activity levels designating a value for a dimension of the plurality of dimensions.

50 . The product of claim 49 , wherein the plurality of dimensions includes a dimension representing a trajectory between a semantic concept and one of a prior semantic concept or a subsequent semantic concept in a string of semantic concepts, the at least one processor further to increment an activity level for the dimension representing the trajectory each time the at least one processor identifies a string of semantic concepts that invokes the trajectory.