Pattern recognition system utilizing self-replicating nodes

A method for performing pattern recognition using a hierarchical network made up of self-replicating fractal cognitive computing nodes (FCNs) arranged with a parent-child relationship in layers, the method comprising:

• at each FCN in the hierarchical network:
• performing a comparison between a respective set of input tuples and a respective set of tuples stored in a respective memory of the FCN, wherein the respective set of input tuples comprises a first respective set of tuples from a respective child FCN or an external input, a second respective set of tuples from a respective parent FCN;
• or both, the comparison determining a respective set of similarity measures, each similarity measure corresponding to a comparison between a tuple in the respective set of input tuples and a tuple in the respective set of tuples stored in the respective memory of the FCN;
• in response to a respective similarity measure from the respective set of similarity measures being less than a similarity threshold, adding the respective set of tuples stored in the memory that correspond to the respective similarity measure to a respective output set;
• in response to each respective similarity measure in the respective set of similarity measures being greater than the similarity threshold, adding the input set of tuples to the respective output set and to the respective memory of the FCN;
• providing the respective output set to the respective parent FCN as the first respective set of tuples, to the respective child FCN as the second respective set of tuples, or to both;
• wherein each tuple in the respective input set of tuples, the respective output set of tuples, the first respective tuple, and the second respective tuple comprise a respective key and a respective value, the respective key being a respective identifier of the tuple and the respective value being a respective magnitude of activation of the respective identifier;
• and
• wherein the respective external input provides respective external tuples to be analyzed by the hierarchical network.

A non-transitory computer readable storage medium having computer readable code thereon, the non-transitory computer readable medium including instructions configured to cause a computer system to perform operations comprising:

• implementing a set of fractal cognitive computing nodes (FCNs), wherein the set of FCNs is configured into a hierarchical network, the set of FCNs having child FCNs at lower levels of the hierarchical network coupled to parent FCNs at higher levels of the hierarchical network, each lower level of the hierarchical network having a respective lower resolution than each higher level of the hierarchical network;
• wherein each child FCN is configured to:
• provide a first respective set of tuples to a respective parent FCN connected thereto, each tuple in the first respective set of tuples comprising a first respective key and a first respective value, the first respective key being a first respective identifier of the tuple and the first respective value being a first respective magnitude of activation of the first respective identifier;
• receive a second respective set of tuples from the respective parent FCN connected thereto or a respective input connection, each tuple in the second respective set of tuples comprising a second respective key and a second respective value, the second respective key being a second respective identifier of the tuple and the second respective value being a second respective magnitude of activation of the second respective identifier, the respective input connection providing data to be analyzed by the pattern recognition system;
• wherein each parent FCN is configured to receive the first respective set of tuples from and provide the second respective set of tuples to respective child FCNs connected thereto;
• wherein each FCN is configured to:
• determine, using the one or more processors, a respective similarity measure between each stored tuple in the memory and a respective set of input tuples, the respective set of input tuples comprising the first respective set of tuples from a respective child FCN or the input connection, the second respective set of tuples from respective parent FCN, or both;
• compare, using the one or more processors, the respective similarity measure to a spatial attention (SA) parameter;
• in response to the respective similarity measure being lower than the SA parameter, add the stored tuple in the memory that corresponds to the respective similarity measure to a respective output set;
• in response to each of the respective similarity measures being greater than the SA parameter, add the respective set of input tuples to the respective output set and a new stored tuple in the memory;
• assign the respective output set as the first respective set of tuples, the second respective set of tuples, or both for the FCN;
• and
• replicate itself into one or more respective child FCNs at a respective lower level of the hierarchical network;
• and
• wherein the pattern recognition system is configured to output the respective output sets for FCNs at the highest level of the hierarchical network.