DEEP LEARNING IN BIPARTITE MEMRISTIVE NETWORKS

Abstract

A bipartite memristive network and method of teaching such a network is described herein. In one example case, the memristive network can include a number of nanofibers, wherein each nanofiber comprises a metallic core and a memristive shell. The memristive network can also include a number of electrodes deposited upon the nanofibers. A first set of the number of electrodes can include input electrodes in the memristive network, and a second set of the number of electrodes can include output electrodes in the memristive network. The memristive network can be embodied as a bipartite memristive network and trained according to the method of teaching described herein.

Description

Claims

1. A method to train a memristive network comprising a number of input nodes and a number of output nodes, comprising: applying an input voltage or current to an input node among the number of input nodes;grounding an output node among the number of output nodes;measuring an output current or voltage at the output node;comparing the measured output current or voltage to a target current or voltage to determine an error delta, where the error delta is a difference between the target current or voltage and the measured output current or voltage;applying a threshold voltage or current to the output node for a time period proportional to a magnitude of the error delta;transforming the error delta into a second error delta;grounding an input node among the number of input nodes; andapplying the threshold voltage or current to the input node for a second time period proportional to the second error delta.

2. The method of claim 1, wherein, when the error delta is negative, applying the threshold voltage or current to the output node comprises: applying a positive threshold voltage or current to the output node for the time period proportional to the error delta; andapplying a negative threshold voltage or current to the output node for the time period proportional to the error delta.

3. The method of claim 1, wherein, when the error delta is positive, applying the threshold voltage or current to the output node comprises: reversing a polarity of the input voltage or current applied to the input node;applying a positive threshold voltage or current to the output node for the time period proportional to the error delta; andapplying a negative threshold voltage or current to the output node for the time period proportional to the error delta.

4. The method of claim 1, wherein: the second error delta comprises an error delta voltage or current; andthe method further comprises: applying the error delta voltage or current to the output node; andapplying the threshold voltage or current to the input node for the second time period, the second time period being proportional to an absolute value of the error delta voltage or current.

5. The method of claim 4, wherein, when the input voltage or current applied to the input node was positive, applying the threshold voltage or current to the input node comprises: applying a positive threshold voltage or current to the input node for the second time period proportional to the absolute value of the error delta voltage or current; andapplying a negative threshold voltage or current to the input node for the second time period proportional to the absolute value of the error delta voltage or current.

6. The method of claim 4, wherein, when the input voltage or current applied to the input node was negative, applying the threshold voltage or current to the input node comprises: reversing a polarity of the error delta voltage or current applied to the output node;applying a positive threshold voltage or current to the input node for the second time period proportional to the absolute value of the error delta voltage or current; andapplying a negative threshold voltage or current to the input node for the second time period proportional to the absolute value of the error delta voltage.

7. The method of claim 1, wherein the memristive network further comprises: a memristive network of memristive nanofibers; andinternal electrodes electrically coupled between the number of input nodes and the number of output nodes by memristive shells of the memristive nanofibers.

8. The method of claim 1, wherein the method reproduces a backpropagation algorithm for training the memristive network of memristive nanofibers.

9. A memristive network, comprising: a number of nanofibers, wherein each nanofiber comprises a metallic core and a memristive shell;a number of electrodes deposited upon the nanofibers, wherein the number of electrodes comprise a number of input nodes and a number of output nodes; anda training processor configured to: apply an input voltage or current to an input node among the number of input nodes;ground an output node among the number of output nodes;measure an output current or voltage at the output node;compare the measured output current or voltage to a target current or voltage to determine an error delta, where the error delta is a difference between the target current or voltage and the measured output current or voltage;apply a threshold voltage or current to the output node for a time period proportional to a magnitude of the error delta;transform the error delta into a second error delta;ground an input node among the number of input nodes; andapply the threshold voltage or current to the input node for a second time period proportional to the second error delta.

10. The memristive network according to claim 9, wherein, when the error delta is negative, the training processor is further configured to: apply a positive threshold voltage or current to the output node for the time period proportional to the error delta; andapply a negative threshold voltage or current to the output node for the time period proportional to the error delta.

11. The memristive network according to claim 9, wherein, when the error delta is positive, the training processor is further configured to: reverse a polarity of the input voltage or current applied to the input node;apply a positive threshold voltage or current to the output node for the time period proportional to the error delta; andapply a negative threshold voltage or current to the output node for the time period proportional to the error delta.

12. The memristive network according to claim 9, wherein: the second error delta comprises an error delta voltage or current; and the training processor is further configured to: apply the error delta voltage or current to the output node; andapply the threshold voltage or current to the input node for the second time period, the second time period being proportional to an absolute value of the error delta voltage or current.

13. The memristive network according to claim 12, wherein, when the input voltage or current applied to the input node was positive, the training processor is further configured to: apply a positive threshold voltage or current to the input node for the second time period proportional to the absolute value of the error delta voltage or current; andapply a negative threshold voltage or current to the input node for the second time period proportional to the absolute value of the error delta voltage or current.

14. The memristive network according to claim 12, wherein, when the input voltage or current applied to the input node was negative, the training processor is further configured to: reverse a polarity of the error delta voltage or current applied to the output node;apply a positive threshold voltage or current to the input node for the second time period proportional to the absolute value of the error delta voltage or current; andapply a negative threshold voltage or current to the input node for the second time period proportional to the absolute value of the error delta voltage.

15. The memristive network according to claim 9, wherein the memristive network further comprises: a memristive network of memristive nanofibers; andinternal electrodes electrically coupled between the number of input nodes and the number of output nodes by memristive shells of the memristive nanofibers.

16. A method to train a memristive network comprising a number of input nodes and a number of output nodes, comprising: applying an input voltage to an input node among the number of input nodes;grounding an output node among the number of output nodes;measuring an output current at the output node;comparing the measured output current to a target current to determine an error delta, where the error delta is a difference between the target current or voltage and the measured output current or voltage;applying a threshold voltage to the output node for a time period proportional to a magnitude of the error delta;transforming the error delta into a second error delta;grounding an input node among the number of input nodes; andapplying the threshold voltage to the input node for a second time period proportional to the second error delta.

17. The method of claim 16, wherein, when the error delta is negative, applying the threshold voltage to the output node comprises: applying a positive threshold voltage to the output node for the time period proportional to the error delta; andapplying a negative threshold voltage to the output node for the time period proportional to the error delta.

18. The method of claim 16, wherein, when the error delta is positive, applying the threshold voltage to the output node comprises: reversing a polarity of the input voltage applied to the input node;applying a positive threshold voltage to the output node for the time period proportional to the error delta; andapplying a negative threshold voltage to the output node for the time period proportional to the error delta.

19. The method of claim 16, wherein the memristive network further comprises: a memristive network of memristive nanofibers; andinternal electrodes electrically coupled between the number of input nodes and the number of output nodes by memristive shells of the memristive nanofibers.

20. The method of claim 16, wherein the method reproduces a backpropagation algorithm for training the memristive network of memristive nanofibers.