UNSUPERVISED, SUPERVISED AND REINFORCED LEARNING VIA SPIKING COMPUTATION

• US 20170213133A1
• Filed: 05/23/2016
• Published: 07/27/2017
• Est. Priority Date: 09/16/2011
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Modha, Dharmendra S.
• Granted Patent: US 10,445,642 B2
• Time in Patent Office: 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 3/063 using electronic means
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 3/088 Non-supervised learning, e.g. competitive learning

Abstract

The present invention relates to unsupervised, supervised and reinforced learning via spiking computation. The neural network comprises a plurality of neural modules. Each neural module comprises multiple digital neurons such that each neuron in a neural module has a corresponding neuron in another neural module. An interconnection network comprising a plurality of edges interconnects the plurality of neural modules. Each edge interconnects a first neural module to a second neural module, and each edge comprises a weighted synaptic connection between every neuron in the first neural module and a corresponding neuron in the second neural module.

Claims

1. A method, comprising:

receiving output generated by a neuron population of a neural network;

determining a type of the output; and

propagating the output through the neural network based on the type of the output.

2. The method of claim 1, wherein the determining comprises:

determining whether the output is a first type or a second type, wherein the first type represents positive output, and the second type represents negative output.

3. The method of claim 2, wherein the propagating comprises:

in response to determining the output is a first type, providing the output to a first set of neuron populations of the neural network, wherein the output is learned as the output propagates through the first set of neuron populations via a first set of pathways.

4. The method of claim 3, wherein the propagating further comprises:

in response to determining the output is a first type, applying Hebb learning based on firing activity of the first set of neuron populations to adjust synaptic weights of the first set of pathways.

5. The method of claim 4, wherein the propagating further comprises:

in response to determining the output is a second type, providing the output to a second set of neuron populations of the neural network, wherein the output is unlearned as the output propagates through the second set of neuron populations via a second set of pathways.

6. The method of claim 5, wherein the propagating further comprises:

in response to determining the output is a second type, applying anti-Hebb learning based on firing activity of the second set of neuron populations to adjust synaptic weights of the second set of pathways.

7. A system comprising a computer processor, a computer-readable hardware storage medium, and program code embodied with the computer-readable hardware storage medium for execution by the computer processor to implement a method comprising:

receiving output generated by a neuron population of a neural network;

determining a type of the output; and

propagating the output through the neural network based on the type of the output.

8. The system of claim 7, wherein the determining comprises:

determining whether the output is a first type or a second type, wherein the first type represents positive output, and the second type represents negative output.

9. The system of claim 8, wherein the propagating comprises:

in response to determining the output is a first type, providing the output to a first set of neuron populations of the neural network, wherein the output is learned as the output propagates through the first set of neuron populations via a first set of pathways.

10. The system of claim 9, wherein the propagating further comprises:

in response to determining the output is a first type, applying Hebb learning based on firing activity of the first set of neuron populations to adjust synaptic weights of the first set of pathways.

11. The system of claim 10, wherein the propagating further comprises:

in response to determining the output is a second type, providing the output to a second set of neuron populations of the neural network, wherein the output is unlearned as the output propagates through the second set of neuron populations via a second set of pathways.

12. The system of claim 11, wherein the propagating further comprises:

in response to determining the output is a second type, applying anti-Hebb learning based on firing activity of the second set of neuron populations to adjust synaptic weights of the second set of pathways.

13. A computer program product comprising a computer-readable hardware storage device having program code embodied therewith, the program code being executable by a computer to implement a method comprising:

receiving output generated by a neuron population of a neural network;

determining a type of the output; and

propagating the output through the neural network based on the type of the output.

14. The computer program product of claim 13, wherein the determining comprises:

determining whether the output is a first type or a second type, wherein the first type represents positive output, and the second type represents negative output.

15. The computer program product of claim 14, wherein the propagating comprises:

in response to determining the output is a first type, providing the output to a first set of neuron populations of the neural network, wherein the output is learned as the output propagates through the first set of neuron populations via a first set of pathways.

16. The computer program product of claim 15, wherein the propagating further comprises:

in response to determining the output is a first type, applying Hebb learning based on firing activity of the first set of neuron populations to adjust synaptic weights of the first set of pathways.

17. The computer program product of claim 16, wherein the propagating further comprises:

in response to determining the output is a second type, providing the output to a second set of neuron populations of the neural network, wherein the output is unlearned as the output propagates through the second set of neuron populations via a second set of pathways.

18. The computer program product of claim 17, wherein the propagating further comprises:

in response to determining the output is a second type, applying anti-Hebb learning based on firing activity of the second set of neuron populations to adjust synaptic weights of the second set of pathways.