Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Linares-Barranco, Alejandro, Prono, Luciano, Lengenstein, Robert, Indiveri, Giacomo, Frenkel, Charlotte
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2405.12849
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910469011275776
author Linares-Barranco, Alejandro
Prono, Luciano
Lengenstein, Robert
Indiveri, Giacomo
Frenkel, Charlotte
author_facet Linares-Barranco, Alejandro
Prono, Luciano
Lengenstein, Robert
Indiveri, Giacomo
Frenkel, Charlotte
contents With the rise of artificial intelligence, neural network simulations of biological neuron models are being explored to reduce the footprint of learning and inference in resource-constrained task scenarios. A mainstream type of such networks are spiking neural networks (SNNs) based on simplified Integrate and Fire models for which several hardware accelerators have emerged. Among them, the ReckOn chip was introduced as a recurrent SNN allowing for both online training and execution of tasks based on arbitrary sensory modalities, demonstrated for vision, audition, and navigation. As a fully digital and open-source chip, we adapted ReckOn to be implemented on a Xilinx Multiprocessor System on Chip system (MPSoC), facilitating its deployment in embedded systems and increasing the setup flexibility. We present an overview of the system, and a Python framework to use it on a Pynq ZU platform. We validate the architecture and implementation in the new scenario of robotic arm control, and show how the simulated accuracy is preserved with a peak performance of 3.8M events processed per second.
format Preprint
id arxiv_https___arxiv_org_abs_2405_12849
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adaptive Robotic Arm Control with a Spiking Recurrent Neural Network on a Digital Accelerator
Linares-Barranco, Alejandro
Prono, Luciano
Lengenstein, Robert
Indiveri, Giacomo
Frenkel, Charlotte
Hardware Architecture
Artificial Intelligence
With the rise of artificial intelligence, neural network simulations of biological neuron models are being explored to reduce the footprint of learning and inference in resource-constrained task scenarios. A mainstream type of such networks are spiking neural networks (SNNs) based on simplified Integrate and Fire models for which several hardware accelerators have emerged. Among them, the ReckOn chip was introduced as a recurrent SNN allowing for both online training and execution of tasks based on arbitrary sensory modalities, demonstrated for vision, audition, and navigation. As a fully digital and open-source chip, we adapted ReckOn to be implemented on a Xilinx Multiprocessor System on Chip system (MPSoC), facilitating its deployment in embedded systems and increasing the setup flexibility. We present an overview of the system, and a Python framework to use it on a Pynq ZU platform. We validate the architecture and implementation in the new scenario of robotic arm control, and show how the simulated accuracy is preserved with a peak performance of 3.8M events processed per second.
title Adaptive Robotic Arm Control with a Spiking Recurrent Neural Network on a Digital Accelerator
topic Hardware Architecture
Artificial Intelligence
url https://arxiv.org/abs/2405.12849