Deep-Unrolling Multidimensional Harmonic Retrieval Algorithms on Neuromorphic Hardware
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909417301082112 |
|---|---|
| author | Andrei, Vlad C. Drăguţoiu, Alexandru P. Béna, Gabriel Akl, Mahmoud Li, Yin Lohrmann, Matthias Mönich, Ullrich J. Boche, Holger |
| author_facet | Andrei, Vlad C. Drăguţoiu, Alexandru P. Béna, Gabriel Akl, Mahmoud Li, Yin Lohrmann, Matthias Mönich, Ullrich J. Boche, Holger |
| contents | This paper explores the potential of conversion-based neuromorphic algorithms for highly accurate and energy-efficient single-snapshot multidimensional harmonic retrieval (MHR). By casting the MHR problem as a sparse recovery problem, we devise the currently proposed, deep-unrolling-based Structured Learned Iterative Shrinkage and Thresholding (S-LISTA) algorithm to solve it efficiently using complex-valued convolutional neural networks with complex-valued activations, which are trained using a supervised regression objective. Afterward, a novel method for converting the complex-valued convolutional layers and activations into spiking neural networks (SNNs) is developed. At the heart of this method lies the recently proposed Few Spikes (FS) conversion, which is extended by modifying the neuron model's parameters and internal dynamics to account for the inherent coupling between real and imaginary parts in complex-valued computations. Finally, the converted SNNs are mapped onto the SpiNNaker2 neuromorphic board, and a comparison in terms of estimation accuracy and power efficiency between the original CNNs deployed on an NVIDIA Jetson Xavier and the SNNs is being conducted. The measurement results show that the converted SNNs achieve almost five-fold power efficiency at moderate performance loss compared to the original CNNs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_04008 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Deep-Unrolling Multidimensional Harmonic Retrieval Algorithms on Neuromorphic Hardware Andrei, Vlad C. Drăguţoiu, Alexandru P. Béna, Gabriel Akl, Mahmoud Li, Yin Lohrmann, Matthias Mönich, Ullrich J. Boche, Holger Signal Processing Artificial Intelligence Hardware Architecture Neural and Evolutionary Computing This paper explores the potential of conversion-based neuromorphic algorithms for highly accurate and energy-efficient single-snapshot multidimensional harmonic retrieval (MHR). By casting the MHR problem as a sparse recovery problem, we devise the currently proposed, deep-unrolling-based Structured Learned Iterative Shrinkage and Thresholding (S-LISTA) algorithm to solve it efficiently using complex-valued convolutional neural networks with complex-valued activations, which are trained using a supervised regression objective. Afterward, a novel method for converting the complex-valued convolutional layers and activations into spiking neural networks (SNNs) is developed. At the heart of this method lies the recently proposed Few Spikes (FS) conversion, which is extended by modifying the neuron model's parameters and internal dynamics to account for the inherent coupling between real and imaginary parts in complex-valued computations. Finally, the converted SNNs are mapped onto the SpiNNaker2 neuromorphic board, and a comparison in terms of estimation accuracy and power efficiency between the original CNNs deployed on an NVIDIA Jetson Xavier and the SNNs is being conducted. The measurement results show that the converted SNNs achieve almost five-fold power efficiency at moderate performance loss compared to the original CNNs. |
| title | Deep-Unrolling Multidimensional Harmonic Retrieval Algorithms on Neuromorphic Hardware |
| topic | Signal Processing Artificial Intelligence Hardware Architecture Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2412.04008 |