Implementation of Kalman Filtering with Spiking Neural Networks
A Kalman filter can be used to fill space–state reconstruction dynamics based on knowledge of a system and partial measurements. However, its performance relies on accurate modeling of the system dynamics and a proper characterization of the uncertainties, which can be hard to obtain in real-life sc...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/22/8845 |
| _version_ | 1797463988762574848 |
|---|---|
| author | Alejandro Juárez-Lora Luis M. García-Sebastián Victor H. Ponce-Ponce Elsa Rubio-Espino Herón Molina-Lozano Humberto Sossa |
| author_facet | Alejandro Juárez-Lora Luis M. García-Sebastián Victor H. Ponce-Ponce Elsa Rubio-Espino Herón Molina-Lozano Humberto Sossa |
| author_sort | Alejandro Juárez-Lora |
| collection | DOAJ |
| description | A Kalman filter can be used to fill space–state reconstruction dynamics based on knowledge of a system and partial measurements. However, its performance relies on accurate modeling of the system dynamics and a proper characterization of the uncertainties, which can be hard to obtain in real-life scenarios. In this work, we explore how the values of a Kalman gain matrix can be estimated by using spiking neural networks through a combination of biologically plausible neuron models with spike-time-dependent plasticity learning algorithms. The performance of proposed neural architecture is verified with simulations of some representative nonlinear systems, which show promising results. This approach traces a path for its implementation in neuromorphic analog hardware that can learn and reconstruct partial and changing dynamics of a system without the massive power consumption that is typically needed in a Von Neumann-based computer architecture. |
| first_indexed | 2024-03-09T18:00:33Z |
| format | Article |
| id | doaj.art-ea782aa3074e4f5383dd4273eadba744 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T18:00:33Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-ea782aa3074e4f5383dd4273eadba7442023-11-24T09:56:43ZengMDPI AGSensors1424-82202022-11-012222884510.3390/s22228845Implementation of Kalman Filtering with Spiking Neural NetworksAlejandro Juárez-Lora0Luis M. García-Sebastián1Victor H. Ponce-Ponce2Elsa Rubio-Espino3Herón Molina-Lozano4Humberto Sossa5Instituto Politécnico Nacional, Centro de Investigación en Computación, Mexico City 07738, MexicoInstituto Politécnico Nacional, Centro de Investigación en Computación, Mexico City 07738, MexicoInstituto Politécnico Nacional, Centro de Investigación en Computación, Mexico City 07738, MexicoInstituto Politécnico Nacional, Centro de Investigación en Computación, Mexico City 07738, MexicoInstituto Politécnico Nacional, Centro de Investigación en Computación, Mexico City 07738, MexicoInstituto Politécnico Nacional, Centro de Investigación en Computación, Mexico City 07738, MexicoA Kalman filter can be used to fill space–state reconstruction dynamics based on knowledge of a system and partial measurements. However, its performance relies on accurate modeling of the system dynamics and a proper characterization of the uncertainties, which can be hard to obtain in real-life scenarios. In this work, we explore how the values of a Kalman gain matrix can be estimated by using spiking neural networks through a combination of biologically plausible neuron models with spike-time-dependent plasticity learning algorithms. The performance of proposed neural architecture is verified with simulations of some representative nonlinear systems, which show promising results. This approach traces a path for its implementation in neuromorphic analog hardware that can learn and reconstruct partial and changing dynamics of a system without the massive power consumption that is typically needed in a Von Neumann-based computer architecture.https://www.mdpi.com/1424-8220/22/22/8845Kalman filterartificial intelligencespiking neural networksroboticsdynamics |
| spellingShingle | Alejandro Juárez-Lora Luis M. García-Sebastián Victor H. Ponce-Ponce Elsa Rubio-Espino Herón Molina-Lozano Humberto Sossa Implementation of Kalman Filtering with Spiking Neural Networks Sensors Kalman filter artificial intelligence spiking neural networks robotics dynamics |
| title | Implementation of Kalman Filtering with Spiking Neural Networks |
| title_full | Implementation of Kalman Filtering with Spiking Neural Networks |
| title_fullStr | Implementation of Kalman Filtering with Spiking Neural Networks |
| title_full_unstemmed | Implementation of Kalman Filtering with Spiking Neural Networks |
| title_short | Implementation of Kalman Filtering with Spiking Neural Networks |
| title_sort | implementation of kalman filtering with spiking neural networks |
| topic | Kalman filter artificial intelligence spiking neural networks robotics dynamics |
| url | https://www.mdpi.com/1424-8220/22/22/8845 |
| work_keys_str_mv | AT alejandrojuarezlora implementationofkalmanfilteringwithspikingneuralnetworks AT luismgarciasebastian implementationofkalmanfilteringwithspikingneuralnetworks AT victorhponceponce implementationofkalmanfilteringwithspikingneuralnetworks AT elsarubioespino implementationofkalmanfilteringwithspikingneuralnetworks AT heronmolinalozano implementationofkalmanfilteringwithspikingneuralnetworks AT humbertosossa implementationofkalmanfilteringwithspikingneuralnetworks |