Memristive neural processor utilizing anti-hebbian and hebbian technology

• US 9,269,043 B2
• Filed: 06/03/2013
• Issued: 02/23/2016
• Est. Priority Date: 03/12/2002
• Status: Expired due to Term

• Current Assignee: Knowm Tech LLC
• Original Assignee: Knowm Tech LLC
• Inventors: Nugent, Alex
• Primary Examiner(s): Gaffin, Jeffrey A
• Assistant Examiner(s): Misir, Dave
• Application Number:
  US13/908,410
• Publication Number:
  US 20140156576A1
• Time in Patent Office: 995 Days
• Field of Search: 706/21, 706/25
• US Class Current: 1/1
• CPC Class Codes: G06N 3/049 Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs

Abstract

An AHaH (Anti-Hebbian and Hebbian) apparatus for use in electronic circuits. Such an AHaH apparatus can include one or more meta-stable switches, and one or more differential pairs of output electrodes, wherein each electrode among each differential pair of output electrodes can include one or more input lines coupled thereto via one or more of the meta-stable switch.

Claims

1. An AHaH (Anti-Hebbian and Hebbian) apparatus for use in electronic circuits, said apparatus comprising:

at least one meta-stable switch driven by an AHaH rule; and

a differential pair of output electrodes, wherein each electrode among said differential pair of output electrodes comprises a plurality of input lines coupled thereto via said at least one meta-stable switch.

2. The apparatus of claim 1 wherein said at least one meta-stable switch comprises a two-state element that switches probabilistically between two states as a function of applied bias and temperature.

3. The apparatus of claim 1 further comprising at least one AHaH node comprising said at least one metal-stable switch and said differential pair of output electrodes.

4. The apparatus of claim 3 further comprising an AHaH classifier that includes said at least one AHaH node.

5. The apparatus of claim 3 further comprising an AHaH clusterer that includes said at least one AHaH node.

6. The apparatus of claim 2 further comprising at least one AHaH node comprising said at least one metal-stable switch and said differential pair of output electrodes.

7. The apparatus of claim 6 further comprising an AHaH classifier that includes said at least one AHaH node.

8. The apparatus of claim 6 further comprising an AHaH clusterer that includes said at least one AHaH node.

9. The apparatus of claim 1 further comprising a synaptic component comprising said at least one meta-stable switch and said differential pair of output electrodes.

10. A memristor for use in electronic circuits, said memristor comprising:

at least one AHaH node comprising at least one meta-stable switch driven by an AHaH rule and a differential pair of output electrodes;

a plurality of input lines, wherein each electrode among said differential pair of output electrodes comprises said plurality of input lines coupled thereto via said at least one meta-stable switch.

11. The memristor of claim 10 wherein said at least one meta-stable switch comprises a two-state element that switches probabilistically between two states as a function of applied bias and temperature.

12. The memristor of claim 10 further comprising an AHaH classifier that includes said at least one AHaH node.

13. The memristor of claim 10 further comprising an AHaH clusterer that includes said at least one AHaH node.

14. The memristor of claim 11 further comprising an AHaH classifier that includes said at least one AHaH node.

15. The memristor of claim 11 further comprising an AHaH clusterer that includes said at least one AHaH node.

16. The memristor of claim 10 further comprising a synaptic component comprising said at least one meta-stable switch and said differential pair of output electrodes.

17. A memristive neural processor comprising an integrated circuit chip, said integrated circuit chip comprising:

a substrate;

at least one meta-stable switch configured upon said substrate, said at least one meta-stable switch driven by an AHaH rule; and

a differential pair of output electrodes configured upon said substrate, wherein each electrode among said differential pair of output electrodes comprises a plurality of input lines coupled thereto via said at least one meta-stable switch.

18. The memristive neural processor of claim 17 wherein said at least one meta-stable switch comprises a two-state element that switches probabilistically between two states as a function of applied bias and temperature.

19. The memristive neural processor of claim 17 further comprising at least one AHaH node comprising said at least one metal-stable switch and said differential pair of output electrodes.

20. The memristive neural processor of claim 18 further comprising at least one AHaH node comprising said at least one metal-stable switch and said differential pair of output electrodes.