A tunable multi-timescale Indium-Gallium-Zinc-Oxide thin-film transistor neuron towards hybrid solutions for spiking neuromorphic applications
Abstract Spiking neural network algorithms require fine-tuned neuromorphic hardware to increase their effectiveness. Such hardware, mainly digital, is typically built on mature silicon nodes. Future artificial intelligence applications will demand the execution of tasks with increasing complexity an...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-07-01
|
| Series: | Communications Engineering |
| Online Access: | https://doi.org/10.1038/s44172-024-00248-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559403362254848 |
|---|---|
| author | Mauricio Velazquez Lopez Bernabe Linares-Barranco Jua Lee Hamidreza Erfanijazi Alberto Patino-Saucedo Manolis Sifalakis Francky Catthoor Kris Myny |
| author_facet | Mauricio Velazquez Lopez Bernabe Linares-Barranco Jua Lee Hamidreza Erfanijazi Alberto Patino-Saucedo Manolis Sifalakis Francky Catthoor Kris Myny |
| author_sort | Mauricio Velazquez Lopez |
| collection | DOAJ |
| description | Abstract Spiking neural network algorithms require fine-tuned neuromorphic hardware to increase their effectiveness. Such hardware, mainly digital, is typically built on mature silicon nodes. Future artificial intelligence applications will demand the execution of tasks with increasing complexity and over timescales spanning several decades. The multi-timescale requirements for certain tasks cannot be attained effectively enough through the existing silicon-based solutions. Indium-Gallium-Zinc-Oxide thin-film transistors can alleviate the timescale-related shortcomings of silicon platforms thanks to their bellow atto-ampere leakage currents. These small currents enable wide timescale ranges, far beyond what has been feasible through various emerging technologies. Here we have estimated and exploited these low leakage currents to create a multi-timescale neuron that integrates information spanning a range of 7 orders of magnitude and assessed its advantages in larger networks. The multi-timescale ability of this neuron can be utilized together with silicon to create hybrid spiking neural networks capable of effectively executing more complex tasks than their single-technology counterparts. |
| format | Article |
| id | doaj-art-f31ad38533844677ab79ce18dc16604b |
| institution | Kabale University |
| issn | 2731-3395 |
| language | English |
| publishDate | 2024-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Communications Engineering |
| spelling | doaj-art-f31ad38533844677ab79ce18dc16604b2025-01-05T12:31:54ZengNature PortfolioCommunications Engineering2731-33952024-07-013111110.1038/s44172-024-00248-7A tunable multi-timescale Indium-Gallium-Zinc-Oxide thin-film transistor neuron towards hybrid solutions for spiking neuromorphic applicationsMauricio Velazquez Lopez0Bernabe Linares-Barranco1Jua Lee2Hamidreza Erfanijazi3Alberto Patino-Saucedo4Manolis Sifalakis5Francky Catthoor6Kris Myny7EPIC, Large Area Thin-film Transistor Electronics, imecInstituto de Microelectrónica de Sevilla, IMSE-CNM, (CSIC Universidad de Sevilla)School of Information and Communication Engineering, Sungkyunkwan University (SKKU)Instituto de Microelectrónica de Sevilla, IMSE-CNM, (CSIC Universidad de Sevilla)Instituto de Microelectrónica de Sevilla, IMSE-CNM, (CSIC Universidad de Sevilla)Imec The Netherlands, High-Tech Campus 31EPIC, Large Area Thin-film Transistor Electronics, imecEPIC, Large Area Thin-film Transistor Electronics, imecAbstract Spiking neural network algorithms require fine-tuned neuromorphic hardware to increase their effectiveness. Such hardware, mainly digital, is typically built on mature silicon nodes. Future artificial intelligence applications will demand the execution of tasks with increasing complexity and over timescales spanning several decades. The multi-timescale requirements for certain tasks cannot be attained effectively enough through the existing silicon-based solutions. Indium-Gallium-Zinc-Oxide thin-film transistors can alleviate the timescale-related shortcomings of silicon platforms thanks to their bellow atto-ampere leakage currents. These small currents enable wide timescale ranges, far beyond what has been feasible through various emerging technologies. Here we have estimated and exploited these low leakage currents to create a multi-timescale neuron that integrates information spanning a range of 7 orders of magnitude and assessed its advantages in larger networks. The multi-timescale ability of this neuron can be utilized together with silicon to create hybrid spiking neural networks capable of effectively executing more complex tasks than their single-technology counterparts.https://doi.org/10.1038/s44172-024-00248-7 |
| spellingShingle | Mauricio Velazquez Lopez Bernabe Linares-Barranco Jua Lee Hamidreza Erfanijazi Alberto Patino-Saucedo Manolis Sifalakis Francky Catthoor Kris Myny A tunable multi-timescale Indium-Gallium-Zinc-Oxide thin-film transistor neuron towards hybrid solutions for spiking neuromorphic applications Communications Engineering |
| title | A tunable multi-timescale Indium-Gallium-Zinc-Oxide thin-film transistor neuron towards hybrid solutions for spiking neuromorphic applications |
| title_full | A tunable multi-timescale Indium-Gallium-Zinc-Oxide thin-film transistor neuron towards hybrid solutions for spiking neuromorphic applications |
| title_fullStr | A tunable multi-timescale Indium-Gallium-Zinc-Oxide thin-film transistor neuron towards hybrid solutions for spiking neuromorphic applications |
| title_full_unstemmed | A tunable multi-timescale Indium-Gallium-Zinc-Oxide thin-film transistor neuron towards hybrid solutions for spiking neuromorphic applications |
| title_short | A tunable multi-timescale Indium-Gallium-Zinc-Oxide thin-film transistor neuron towards hybrid solutions for spiking neuromorphic applications |
| title_sort | tunable multi timescale indium gallium zinc oxide thin film transistor neuron towards hybrid solutions for spiking neuromorphic applications |
| url | https://doi.org/10.1038/s44172-024-00248-7 |
| work_keys_str_mv | AT mauriciovelazquezlopez atunablemultitimescaleindiumgalliumzincoxidethinfilmtransistorneurontowardshybridsolutionsforspikingneuromorphicapplications AT bernabelinaresbarranco atunablemultitimescaleindiumgalliumzincoxidethinfilmtransistorneurontowardshybridsolutionsforspikingneuromorphicapplications AT jualee atunablemultitimescaleindiumgalliumzincoxidethinfilmtransistorneurontowardshybridsolutionsforspikingneuromorphicapplications AT hamidrezaerfanijazi atunablemultitimescaleindiumgalliumzincoxidethinfilmtransistorneurontowardshybridsolutionsforspikingneuromorphicapplications AT albertopatinosaucedo atunablemultitimescaleindiumgalliumzincoxidethinfilmtransistorneurontowardshybridsolutionsforspikingneuromorphicapplications AT manolissifalakis atunablemultitimescaleindiumgalliumzincoxidethinfilmtransistorneurontowardshybridsolutionsforspikingneuromorphicapplications AT franckycatthoor atunablemultitimescaleindiumgalliumzincoxidethinfilmtransistorneurontowardshybridsolutionsforspikingneuromorphicapplications AT krismyny atunablemultitimescaleindiumgalliumzincoxidethinfilmtransistorneurontowardshybridsolutionsforspikingneuromorphicapplications AT mauriciovelazquezlopez tunablemultitimescaleindiumgalliumzincoxidethinfilmtransistorneurontowardshybridsolutionsforspikingneuromorphicapplications AT bernabelinaresbarranco tunablemultitimescaleindiumgalliumzincoxidethinfilmtransistorneurontowardshybridsolutionsforspikingneuromorphicapplications AT jualee tunablemultitimescaleindiumgalliumzincoxidethinfilmtransistorneurontowardshybridsolutionsforspikingneuromorphicapplications AT hamidrezaerfanijazi tunablemultitimescaleindiumgalliumzincoxidethinfilmtransistorneurontowardshybridsolutionsforspikingneuromorphicapplications AT albertopatinosaucedo tunablemultitimescaleindiumgalliumzincoxidethinfilmtransistorneurontowardshybridsolutionsforspikingneuromorphicapplications AT manolissifalakis tunablemultitimescaleindiumgalliumzincoxidethinfilmtransistorneurontowardshybridsolutionsforspikingneuromorphicapplications AT franckycatthoor tunablemultitimescaleindiumgalliumzincoxidethinfilmtransistorneurontowardshybridsolutionsforspikingneuromorphicapplications AT krismyny tunablemultitimescaleindiumgalliumzincoxidethinfilmtransistorneurontowardshybridsolutionsforspikingneuromorphicapplications |