Neural network learning and collaboration apparatus and methods

• US 9,613,310 B2
• Filed: 12/07/2015
• Issued: 04/04/2017
• Est. Priority Date: 06/01/2012
• Status: Active Grant

• Current Assignee: Brain Corporation
• Original Assignee: Brain Corporation
• Inventors: Buibas, Marius, Izhikevich, Eugene M., Szatmary, Botond, Polonichko, Vadim
• Primary Examiner(s): Hill, Stanley K
• Assistant Examiner(s): Bharadwaj, Kalpana
• Application Number:
  US14/961,522
• Publication Number:
  US 20160155050A1
• Time in Patent Office: 484 Days
• CPC Class Codes: G06N 3/04 Architecture, e.g. interconnection topology
• CPC Class Codes: G06N 3/049 Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 3/10 Interfaces, programming languages or software development kits, e.g. for simulating neural networks

Abstract

Apparatus and methods for learning and training in neural network-based devices. In one implementation, the devices each comprise multiple spiking neurons, configured to process sensory input. In one approach, alternate heterosynaptic plasticity mechanisms are used to enhance learning and field diversity within the devices. The selection of alternate plasticity rules is based on recent post-synaptic activity of neighboring neurons. Apparatus and methods for simplifying training of the devices are also disclosed, including a computer-based application. A data representation of the neural network may be imaged and transferred to another computational environment, effectively copying the brain. Techniques and architectures for achieve this training, storing, and distributing these data representations are also disclosed.

Claims

1. A method of behavioral programming in an artificial neural network, the method comprising:

generating a data link to at least one device configured to run the artificial neural network;

receiving one or more data elements indicating a current status associated with the artificial neural network;

causing display of information related to at least a portion of the one or more data elements;

receiving user input from a user interface;

generating one or more feedback elements based at least in part on the user input; and

transmitting the one or more feedback elements to the artificial neural network via the data link;

wherein the one or more feedback elements cause the artificial neural network to modify responses of a plurality of neurons configured to develop receptive fields to a feature within an input, thereby reducing the number of neurons required to recognize the feature.

2. The method of claim 1, wherein the at least one device that is configured to run the artificial neural network comprises a robot comprising one or more functional modules.

3. The method of claim 2, wherein the one or more functional modules comprise at least one sensory device.

4. The method of claim 3, wherein:

the artificial neural network is configured to generate one or more discrete output signals in response to input from the at least one sensory device; and

the discrete output signals cause an action of at least one of the one or more functional modules.

5. The method of claim 4, wherein:

the displayed information comprises one or more visual representations of the input from the sensor; and

at least one indicator configured to indicate one or more neurons involved in the generation of the one or more discrete output signals.

6. The method of claim 1, wherein the display and the user interface are disposed on a mobile wireless-enabled device.

7. The method of claim 6, wherein the generated data link is effected via at least a personal area network.

8. The method of claim 6, wherein the generated data link comprises a data session over at least a Wi-Fi compliant connection.

9. The method of claim 1, wherein the one or more feedback elements comprise negative feedback designed to suppress an output generated by one or more neurons of the artificial neural network.

10. The method of claim 1, wherein the one or more feedback elements comprise positive feedback to potentiate one or more neurons of the artificial neural network.

11. The method of claim 1, further comprising downloading an image of the artificial neural network to the at least one device from a cloud-based server.

12. The method of claim 11, further comprising causing recommendation of the image via at least one application running on the cloud-based server, the recommendation being based at least in part on a task designated by the user.

13. A non-transitory computer-readable medium configured to store at least one computer program thereon, the at least one computer program comprising instructions being

configured to, when executed:

establish a data link to at least one user device configured to run the artificial neural network;

receive one or more data elements comprising a state profile of the artificial neural network;

transmit at least a portion of the one or more data elements comprising the state profile of

the artificial neural network to the at least one user device;

receive user input from a user interface of the at least one user device;

generate one or more feedback signals based at least in part on the user input; and

transmit the one or more feedback signals to the artificial neural network via the data link;

wherein the one or more feedback elements cause the artificial neural network to modify responses of a plurality of neurons configured to develop receptive fields to a feature within an input, thereby reducing the number of neurons required to recognize the feature.

14. The non-transitory computer-readable medium of claim 13, wherein the instructions are further configured to, when executed, cause display of information related to at least the portion of the one or more data elements comprising the state profile of the artificial neural network.

15. The non-transitory computer-readable medium of claim 13, wherein the display of information and the user interface are disposed on a mobile wireless-enabled device.

16. The non-transitory computer-readable medium of claim 13, wherein the established data link comprises a link operative over a wireless local area network (WLAN) or a personal area network (PAN).

17. The non-transitory computer-readable medium of claim 13, wherein the one or more feedback signals are configured to alter a behavioral trait associated with the artificial neural network.

18. The non-transitory computer-readable medium of claim 17, wherein the alteration of the behavioral trait comprises potentiation of one or more neurons of the artificial neural network.

19. The non-transitory computer-readable medium of claim 17, wherein the alteration of the behavioral trait comprises depression one or more neurons of the artificial neural network.

20. An apparatus configured to behaviorally program an artificial neural network apparatus comprising:

means for generating a data link to at least one user device configured to run the artificial neural network;

means for receiving one or more data elements comprising a state profile of the artificial neural network;

means for causing display of information related to at least a portion of the one or more data elements;

means for receiving user input from a user interface;

means for generating one or more feedback signals based at least in part on the user input; and

means for transmitting the one or more feedback signals to the artificial neural network via the data link;

wherein the one or more feedback elements cause the artificial neural network to modify responses of a plurality of neurons configured to develop receptive fields to a feature within an input, thereby reducing the number of neurons required to recognize the feature.