Neural segmentation of an input signal and applications using simulated neurons, and a phase modulator
Disclosed are systems, methods, and computer-program products for segmenting content of an input signal and applications thereof. In an embodiment, the system includes simulated neurons, a phase modulator, and an entity-identifier module. Each simulated neuron is connected to one or more other simulated neurons and is associated with an activity and a phase. The activity and the phase of each simulated neuron is set based on the activity and the phase of the one or more other simulated neurons connected to each simulated neuron. The phase modulator includes individual modulators, each configured to modulate the activity and the phase of each of the plurality of simulated neurons based on a modulation function. The entity-identifier module is configured to identify one or more distinct entities (e.g., objects, sound sources, etc.) included in the input signal based on the one or more distinct collections of simulated neurons that have substantially distinct phases.
1. A method for processing an input signal using a plurality of simulated neurons, wherein each simulated neuron is connected to one or more other simulated neurons, and each simulated neuron is associated with an activity and a phase, the method comprising:
(a) setting activity and phase of each simulated neuron based on activity and phase of other simulated neurons connected to said each simulated neuron;
(b) modulating activity and phase of each of the plurality of simulated neurons based on a plurality of modulation functions; and
(c) identifying one or more distinct entities in the input signal based on one or more distinct collections of simulated neurons that have substantially distinct phases.
2. The method of claim 1 , further comprising:
establishing connections between simulated neurons based on definitions provided in a network-description file.
3. The method of claim 1 , wherein step (c) comprises:
using a histogram to identify the one or more distinct entities in the input signal.
4. The method of claim 1 , wherein step (c) comprises:
using a selection-cell anatomy to identify the one or more distinct entities in the input signal.
5. The method of claim 1 , wherein the input signal comprises a video signal, and wherein step (c) comprises:
identifying a first object in the video signal based on a first collection of simulated neurons having substantially a first phase; and
identifying a second object in the video signal based on a second collection of simulated neurons having substantially a second phase.
6. The method of claim 1 , wherein the input signal comprises an audio signal, and wherein step (c) comprises:
identifying a first sound source in the audio signal based on a first collection of simulated neurons having substantially a first phase; and
identifying a second sound source in the audio signal based on a second collection of simulated neurons having substantially a second phase.
7. The method of claim 6 , wherein:
the first sound source comprises a first human speaker; and
the second sound source comprises a second human speaker.
8. A computer-program product comprising a computer-readable storage medium having instructions stored thereon that, if executed by a computing device, cause the computing device to perform a method for processing an input signal using a plurality of simulated neurons, wherein each simulated neuron is connected to one or more other simulated neurons, and each simulated neuron is associated with an activity and a phase, the method comprising:
(a) setting activity and phase of each simulated neuron based on activity and phase of other simulated neurons connected to said each simulated neuron;
(b) modulating activity and phase of each of the plurality of simulated neurons based on a plurality of modulation functions; and
(c) identifying one or more distinct entities in the input signal based on one or more distinct collections of simulated neurons that have substantially distinct phases.
9. The computer-program product of claim 8 , wherein the method further comprises:
establishing connections between simulated neurons based on definitions provided in a network-description file.
10. The computer-program product of claim 8 , wherein step (c) of the method comprises:
using a histogram to identify the one or more distinct entities in the input signal.
11. The computer-program product of claim 8 , wherein step (c) of the method comprises:
using a selection-cell anatomy to identify the one or more distinct entities in the input signal.
12. The computer-program product of claim 8 , wherein the input signal comprises a video signal, and wherein step (c) of the method comprises:
identifying a first object in the video signal based on a first collection of simulated neurons having substantially a first phase; and
identifying a second object in the video signal based on a second collection of simulated neurons having substantially a second phase.
13. The computer-program product of claim 8 , wherein the input signal comprises an audio signal, and wherein step (c) of the method comprises:
identifying a first sound source in the audio signal based on a first collection of simulated neurons having substantially a first phase; and
identifying a second sound source in the audio signal based on a second collection of simulated neurons having substantially a second phase.
14. The computer-program product of claim 13 , wherein:
the first sound source comprises a first human speaker; and
the second sound source comprises a second human speaker.
15. A system for processing an input signal, comprising:
a plurality of simulated neurons, each simulated neuron connected to one or more other simulated neurons, and each simulated neuron associated with an activity and a phase, wherein activity and phase of each simulated neuron are configured to be set based on activity and phase of other simulated neurons connected to said each simulated neuron; and
a phase modulator comprising a plurality of individual modulators, each individual modulator configured to modulate activity and phase of each of the plurality of simulated neurons based on a modulation function;
an entity-identifier module configured to identify one or more distinct entities in the input signal based on one or more distinct collections of simulated neurons that have substantially distinct phases.
16. The system of claim 15 , further comprising:
a network-description file that defines how a simulated neuron is to be connected to the one or more other simulated neurons.
17. The system of claim 15 , wherein entity-identifier module is configured to use a histogram to identify the one or more distinct entities in the input signal.
18. The system of claim 15 , wherein entity-identifier module comprises:
a selection-cell anatomy configured to identify the one or more distinct entities in the input signal.
19. The system of claim 15 , wherein:
the input signal comprises a video signal; and
the entity-identifier module is configured to identify (i) a first object in the video signal based on a first collection of simulated neurons having substantially a first phase and (ii) a second object in the video signal based on a second collection of simulated neurons having substantially a second phase.
20. The system of claim 15 , wherein:
the input signal comprises an audio signal; and
the entity-identifier module is configure to identify (i) a first sound source in the audio signal based on a first collection of simulated neurons having substantially a first phase and (ii) a second sound source in the audio signal based on a second collection of simulated neurons having substantially a second phase.
21. The system of claim 20 , wherein:
the first sound source comprises a first human speaker; and
the second sound source comprises a second human speaker.