An integrated toolbox for creating neuromorphic edge applications
spiking neural networks (SNNs) and neuromorphic models are believed to be more efficient in general and have more biological realism than the activation functions typically used in deep neural networks, transformer models and generative AI. SNNs have local learning rules, are able to learn on small...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | Neuromorphic Computing and Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2634-4386/adad0f |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832578890704355328 |
|---|---|
| author | Lars Niedermeier Nikil Dutt Jeffrey L Krichmar |
| author_facet | Lars Niedermeier Nikil Dutt Jeffrey L Krichmar |
| author_sort | Lars Niedermeier |
| collection | DOAJ |
| description | spiking neural networks (SNNs) and neuromorphic models are believed to be more efficient in general and have more biological realism than the activation functions typically used in deep neural networks, transformer models and generative AI. SNNs have local learning rules, are able to learn on small data sets, and can adapt through neuromodulation. Although research has shown their advantages, there are still few compelling practical applications, especially at the edge where sensors and actuators need to be processed in a timely fashion. One reason for this might be that SNNs are much more challenging to understand, build, and operate due to their intrinsic properties. For instance, the mathematical foundation involves differential equations rather than basic activation functions. To address these challenges, we have developed CARLsim++, an integrated toolbox that facilitates the creation of neuromorphic applications. It extends the highly efficient CARLsim open-source SNN simulator. CARLsim++ encapsulates the mathematical intrinsics and low-level C++ programming by providing a graphical user interface for users to easily create their SNNs and a means to configure sensors and actuators for robotics and other edge devices. These can be accurately simulated before deploying on physical devices. CARLsim++ can lead to rapid development of neuromorphic applications for simulation or edge processing. We introduce CARLsim++ with a closed loop robotic demonstration using neuromorphic computing. |
| format | Article |
| id | doaj-art-521ef0dc938d49c8b1b9fab9e93c2bfa |
| institution | Kabale University |
| issn | 2634-4386 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Neuromorphic Computing and Engineering |
| spelling | doaj-art-521ef0dc938d49c8b1b9fab9e93c2bfa2025-01-30T13:21:57ZengIOP PublishingNeuromorphic Computing and Engineering2634-43862025-01-015101400310.1088/2634-4386/adad0fAn integrated toolbox for creating neuromorphic edge applicationsLars Niedermeier0https://orcid.org/0009-0007-1277-4037Nikil Dutt1Jeffrey L Krichmar2https://orcid.org/0000-0003-0739-2468Niedermeier Consulting , Zurich, ZH, SwitzerlandDepartment of Computer Science, University of California , Irvine, CA, United States of AmericaDepartment of Computer Science, University of California , Irvine, CA, United States of America; Department of Cognitive Sciences, University of California , Irvine, CA, United States of Americaspiking neural networks (SNNs) and neuromorphic models are believed to be more efficient in general and have more biological realism than the activation functions typically used in deep neural networks, transformer models and generative AI. SNNs have local learning rules, are able to learn on small data sets, and can adapt through neuromodulation. Although research has shown their advantages, there are still few compelling practical applications, especially at the edge where sensors and actuators need to be processed in a timely fashion. One reason for this might be that SNNs are much more challenging to understand, build, and operate due to their intrinsic properties. For instance, the mathematical foundation involves differential equations rather than basic activation functions. To address these challenges, we have developed CARLsim++, an integrated toolbox that facilitates the creation of neuromorphic applications. It extends the highly efficient CARLsim open-source SNN simulator. CARLsim++ encapsulates the mathematical intrinsics and low-level C++ programming by providing a graphical user interface for users to easily create their SNNs and a means to configure sensors and actuators for robotics and other edge devices. These can be accurately simulated before deploying on physical devices. CARLsim++ can lead to rapid development of neuromorphic applications for simulation or edge processing. We introduce CARLsim++ with a closed loop robotic demonstration using neuromorphic computing.https://doi.org/10.1088/2634-4386/adad0fedge computingneuromorphic applicationsspiking neural networks |
| spellingShingle | Lars Niedermeier Nikil Dutt Jeffrey L Krichmar An integrated toolbox for creating neuromorphic edge applications Neuromorphic Computing and Engineering edge computing neuromorphic applications spiking neural networks |
| title | An integrated toolbox for creating neuromorphic edge applications |
| title_full | An integrated toolbox for creating neuromorphic edge applications |
| title_fullStr | An integrated toolbox for creating neuromorphic edge applications |
| title_full_unstemmed | An integrated toolbox for creating neuromorphic edge applications |
| title_short | An integrated toolbox for creating neuromorphic edge applications |
| title_sort | integrated toolbox for creating neuromorphic edge applications |
| topic | edge computing neuromorphic applications spiking neural networks |
| url | https://doi.org/10.1088/2634-4386/adad0f |
| work_keys_str_mv | AT larsniedermeier anintegratedtoolboxforcreatingneuromorphicedgeapplications AT nikildutt anintegratedtoolboxforcreatingneuromorphicedgeapplications AT jeffreylkrichmar anintegratedtoolboxforcreatingneuromorphicedgeapplications AT larsniedermeier integratedtoolboxforcreatingneuromorphicedgeapplications AT nikildutt integratedtoolboxforcreatingneuromorphicedgeapplications AT jeffreylkrichmar integratedtoolboxforcreatingneuromorphicedgeapplications |