System and method for an adjustable neural network

1 . A method comprising:

measuring, via a processor, feature applicability for an octave of a Convolutional Neural Network (CNN) at a standard scale, resulting in (1) at least one drop-off point where the octave no longer resonates with pre-defined features; and (2) a common drop-off between the CNN and at least one other CNN trained on at least one other separate domain;

measuring, via the processor, octave resonance for a plurality of CNNs trained on large data sets with a distribution of octaves for features;

measuring a pattern of octaves learned in the CNN, resulting in a measurement pattern;

comparing that measurement pattern to the pre-defined features, resulting in a level of adaptability of the CNN; and

modifying the CNN based on the level of adaptability of the CNN, resulting in a modified CNN, wherein the modifying of the CNN further comprises:

identifying, via the processor, at least one layer of the CNN corresponding to the at least one drop-off point;

identifying, via the processor within a database of neural network layers, at least one replacement layer associated which resonates with the pre-defined features; and

replacing, via the processor, the at least one layer of the CNN with the at least one replacement layer, resulting in the modified CNN.

2 . The method of claim 1 , wherein the octave resonance results in only partial overage of the at least one other CNN by the CNN.

3 . The method of claim 1 , wherein the pre-defined features are associated with recognition of a particular type of object having a pre-defined scale, and the replacement layer is associated with a distinct pre-defined scale.

4 . The method of claim 1 , wherein the measuring of feature applicability uses three types of inputs sets: an objective known set, an objective unknown set, and a nonobjective set.

5 . A system comprising:

a processor; and

a non-transitory computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:

measuring feature applicability for an octave of a Convolutional Neural Network (CNN) at a standard scale, resulting in (1) at least one drop-off point where the octave no longer resonates with pre-defined features; and (2) a common drop-off between the CNN and at least one other CNN trained on at least one other separate domain;

measuring octave resonance for a plurality of CNNs trained on large data sets with a distribution of octaves for features;

measuring a pattern of octaves learned in the CNN, resulting in a measurement pattern;

comparing that measurement pattern to the pre-defined features, resulting in a level of adaptability of the CNN; and

modifying the CNN based on the level of adaptability of the CNN, resulting in a modified CNN, wherein the modifying of the CNN further comprises:

identifying at least one layer of the CNN corresponding to the at least one drop-off point;

identifying, within a database of neural network layers, at least one replacement layer associated which resonates with the pre-defined features; and

replacing the at least one layer of the CNN with the at least one replacement layer, resulting in the modified CNN.

6 . The system of claim 5 , wherein the octave resonance results in only partial overage of the at least one other CNN by the CNN.

7 . The system of claim 5 , wherein the pre-defined features are associated with recognition of a particular type of object having a pre-defined scale, and the replacement layer is associated with a distinct pre-defined scale.

8 . The system of claim 5 , wherein the measuring of feature applicability uses three types of inputs sets: an objective known set, an objective unknown set, and a nonobjective set.

9 . A non-transitory computer-readable storage medium having instructions stored which, when executed by a computer system, cause the computer system to perform operations comprising:

measuring feature applicability for an octave of a Convolutional Neural Network (CNN) at a standard scale, resulting in (1) at least one drop-off point where the octave no longer resonates with pre-defined features; and (2) a common drop-off between the CNN and at least one other CNN trained on at least one other separate domain;

measuring octave resonance for a plurality of CNNs trained on large data sets with a distribution of octaves for features;

measuring a pattern of octaves learned in the CNN, resulting in a measurement pattern;

comparing that measurement pattern to the pre-defined features, resulting in a level of adaptability of the CNN; and

modifying the CNN based on the level of adaptability of the CNN, resulting in a modified CNN, wherein the modifying of the CNN further comprises:

identifying at least one layer of the CNN corresponding to the at least one drop-off point;

identifying, within a database of neural network layers, at least one replacement layer associated which resonates with the pre-defined features; and

replacing the at least one layer of the CNN with the at least one replacement layer, resulting in the modified CNN.

10 . The non-transitory computer-readable storage medium of claim 9 , wherein the octave resonance results in only partial overage of the at least one other CNN by the CNN.

11 . The non-transitory computer-readable storage medium of claim 9 , wherein the pre-defined features are associated with recognition of a particular type of object having a pre-defined scale, and the replacement layer is associated with a distinct pre-defined scale.

12 . The non-transitory computer-readable storage medium of claim 9 , wherein the measuring of feature applicability uses three types of inputs sets: an objective known set, an objective unknown set, and a nonobjective set.

13 . A method comprising:

measuring, via a processor, feature applicability for an octave of a Convolutional Neural Network (CNN) at a standard scale, resulting in (1) at least one drop-off point where the octave no longer resonates with pre-defined features; and (2) a common drop-off between the CNN and at least one other CNN trained on at least one other separate domain;

measuring, via the processor, octave resonance for a plurality of CNNs trained on large data sets with a distribution of octaves for features;

measuring a pattern of octaves learned in the CNN, resulting in a measurement pattern;

comparing that measurement pattern to the pre-defined features, resulting in a level of adaptability of the CNN;

modifying the CNN based on the level of adaptability of the CNN, resulting in a modified CNN;

measuring, via the processor, applicability of a new image with the modified CNN;

determining, via the processor based on the applicability meeting a predefined threshold, that the new image represents a new category, resulting in a determination;

generating, based on the determination, a new branch of features associated with the new image; and

adding the new branch of features to the modified CNN, resulting in an updated, modified CNN.

14 . The method of claim 13 , further comprising:

performing additional image recognition using the updated, modified CNN.

15 . A system comprising:

a processor; and

a non-transitory computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:

measuring feature applicability for an octave of a Convolutional Neural Network (CNN) at a standard scale, resulting in (1) at least one drop-off point where the octave no longer resonates with pre-defined features; and (2) a common drop-off between the CNN and at least one other CNN trained on at least one other separate domain;

measuring octave resonance for a plurality of CNNs trained on large data sets with a distribution of octaves for features;

measuring a pattern of octaves learned in the CNN, resulting in a measurement pattern;

comparing that measurement pattern to the pre-defined features, resulting in a level of adaptability of the CNN;

modifying the CNN based on the level of adaptability of the CNN, resulting in a modified CNN;

measuring applicability of a new image with the modified CNN;

determining, based on the applicability meeting a predefined threshold, that the new image represents a new category, resulting in a determination;

generating, based on the determination, a new branch of features associated with the new image; and

adding the new branch of features to the modified CNN, resulting in an updated, modified CNN.

16 . The system of claim 15 , the non-transitory computer-readable storage medium having additional instructions stored which, when executed by the processor, cause the processor to perform operations comprising:

performing additional image recognition using the updated, modified CNN.

17 . A non-transitory computer-readable storage medium having instructions stored which, when executed by a computer system, cause the computer system to perform operations comprising:

measuring feature applicability for an octave of a Convolutional Neural Network (CNN) at a standard scale, resulting in (1) at least one drop-off point where the octave no longer resonates with pre-defined features; and (2) a common drop-off between the CNN and at least one other CNN trained on at least one other separate domain;

measuring octave resonance for a plurality of CNNs trained on large data sets with a distribution of octaves for features;

measuring a pattern of octaves learned in the CNN, resulting in a measurement pattern;

comparing that measurement pattern to the pre-defined features, resulting in a level of adaptability of the CNN;

modifying the CNN based on the level of adaptability of the CNN, resulting in a modified CNN;

measuring applicability of a new image with the modified CNN;

determining, based on the applicability meeting a predefined threshold, that the new image represents a new category, resulting in a determination;

generating, based on the determination, a new branch of features associated with the new image; and

adding the new branch of features to the modified CNN, resulting in an updated, modified CNN.