Associative Memory for Image Recovery with a High‐Performance Memristor Array
Source abstract
Abstract
Abstract Associative memory is one of the significant characteristics of the biological brain. However, it has yet to be realized in a large memristor array due to the high requirements on the memristor device. In this work, the multilevel memristor cell is optimized by employing an electro‐thermal modulation layer. Memristor devices show both high resistance, cell‐to‐cell uniformity, and multilevel resistive switching behaviors with good reliability. A Hopfield neural network is experimentally demonstrated on a 1k memristor array that is capable of realizing the associative memory function for emotion image recovery. By using both asynchronous and synchronous refresh schemes, complete emotion images can be recalled from partial information.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Memory and Neural Computing · Neural dynamics and brain function · CCD and CMOS Imaging Sensors
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Institute of Microelectronics Tsinghua University Beijing 100084 China
Funding
National Natural Science Foundation of China · Ministry of Science and Technology of the People's Republic of China · Beijing Municipal Science and Technology Commission
References (49)
Show source-provided references
1. 10.1007/s11263-015-0816-y10.1007/s11263-015-0816-y ↗
2. 10.1021/acs.nanolett.7b0055210.1021/acs.nanolett.7b00552 ↗
3. 10.1186/s40537-014-0007-710.1186/s40537-014-0007-7 ↗
4. Pavlov P. I. · Ann. Neurosci. · 2010 · 8 · 136
5. Danilo R. · 2015 · 2501
6. 10.1037/0033-295X.84.5.41310.1037/0033-295X.84.5.413 ↗
7. 10.1109/21.8705410.1109/21.87054 ↗
8. Fukuda T. · 2001 · 1210.1007/3-540-44732-6_2 ↗
9. 10.1109/72.47839710.1109/72.478397 ↗
10. 10.1073/pnas.79.8.255410.1073/pnas.79.8.2554 ↗
11. 10.1073/pnas.81.10.308810.1073/pnas.81.10.3088 ↗
12. 10.1007/BF0033994310.1007/BF00339943 ↗
13. 10.1126/science.375525610.1126/science.3755256 ↗
14. 10.1109/31.3132510.1109/31.31325 ↗
15. 10.1038/ncomms852210.1038/ncomms8522 ↗
16. 10.1109/TED.2011.214779110.1109/TED.2011.2147791 ↗
17. 10.1002/adma.20120368010.1002/adma.201203680 ↗
18. 10.1038/nnano.2017.8310.1038/nnano.2017.83 ↗
19. 10.1038/nature1444110.1038/nature14441 ↗
20. Wu H. · 2017 · 11.5.110.1109/IEDM.2017.8268372 ↗
21. 10.1002/adma.20170591410.1002/adma.201705914 ↗
22. Park S. · 2013 · 25.6.110.1109/IEDM.2013.6724692 ↗
23. 10.1038/ncomms1280510.1038/ncomms12805 ↗
24. 10.1039/C6NR04142F10.1039/C6NR04142F ↗
25. 10.1088/0957-4484/24/38/38401210.1088/0957-4484/24/38/384012 ↗
26. 10.1038/s41467-017-02337-y10.1038/s41467-017-02337-y ↗
27. 10.1038/s41467-018-04484-210.1038/s41467-018-04484-2 ↗
28. 10.1038/s42256-018-0001-410.1038/s42256-018-0001-4 ↗
29. 10.1038/s41928-017-0002-z10.1038/s41928-017-0002-z ↗
30. 10.1038/ncomms1519910.1038/ncomms15199 ↗
31. 10.3389/fnins.2014.0020510.3389/fnins.2014.00205 ↗
32. Eryilmaz S. B. · 2015 · 4.1.110.1109/IEDM.2015.7409622 ↗
33. Milo V. · 2017 · 11.2.110.1109/IEDM.2017.8268369 ↗
34. 10.1039/C4NR00500G10.1039/C4NR00500G ↗
35. 10.1109/LED.2016.254287910.1109/LED.2016.2542879 ↗
36. Wu M. C. · Semicond. Sci. Technol. · 2012 · 27 · 68
37. 10.1109/LED.2014.237520010.1109/LED.2014.2375200 ↗
38. 10.1109/TED.2013.224550810.1109/TED.2013.2245508 ↗
39. Yan B. · 2016 · 1390
40. 10.1109/TNANO.2017.278436410.1109/TNANO.2017.2784364 ↗
41. 10.1016/j.microrel.2014.07.13510.1016/j.microrel.2014.07.135 ↗
42. Fantini A. · 2013 · 3010.1109/IMW.2013.6582090 ↗
43. 10.1109/TIT.1987.105732810.1109/TIT.1987.1057328 ↗
44. 10.1109/82.28570610.1109/82.285706 ↗
45. 10.1109/JPROC.2012.219036910.1109/JPROC.2012.2190369 ↗
46. Wu W. · 2018 · 10310.1109/VLSIT.2018.8510690 ↗
47. 10.1088/0957-4484/27/39/39520110.1088/0957-4484/27/39/395201 ↗
48. Traoré B. · 2014 · 21.5.110.1109/IEDM.2014.7047097 ↗
49. Gao B. · 2017 · 4.4.110.1109/IEDM.2017.8268326 ↗