Comparing Loihi with a SpiNNaker 2 prototype on low-latency keyword spotting and adaptive robotic control

Yan, Yexin; Stewart, Terrence C.; Choo, Xuan; Vogginger, Bernhard; Partzsch, Johannes; Höppner, Sebastian; Kelber, Florian; Eliasmith, Chris; Furber, Steve; Mayr, Christian

doi:10.1088/2634-4386/abf150

Cited by 35 publications

(30 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Robotic arms In ref. 155 the authors compared two different platforms, Loihi and SpiNNaker2 on a common benchmark, the control of a robotic arm, in terms of computation time and active energy. Both platforms are efficient in specific parameter regions, SpiNNaker2 is more efficient when the number of input dimensions is high, while Loihi is more efficient when the number of input dimensions is low.…”

Section: Box 3 | Neuromorphic Robotsmentioning

confidence: 99%

Embodied neuromorphic intelligence

2022

View full text Add to dashboard Cite

The design of robots that interact autonomously with the environment and exhibit complex behaviours is an open challenge that can benefit from understanding what makes living beings fit to act in the world. Neuromorphic engineering studies neural computational principles to develop technologies that can provide a computing substrate for building compact and low-power processing systems. We discuss why endowing robots with neuromorphic technologies – from perception to motor control – represents a promising approach for the creation of robots which can seamlessly integrate in society. We present initial attempts in this direction, highlight open challenges, and propose actions required to overcome current limitations.

show abstract

Section: Box 3 | Neuromorphic Robotsmentioning

confidence: 99%

Embodied neuromorphic intelligence

2022

View full text Add to dashboard Cite

show abstract

“…In [80], Blouw and co-workers benchmark different hardware performing keyword spotting tasks, showing a significantly reduced energy consumption when using Intel's Loihi chip. Researchers' achievements using Loihi are summarized in [33], and the platform has also been compared with a SpiNNaker 2 prototype by Yan et al [81].…”

Section: Benchmarks and Iot Applications Of Neuromorphic Solutionsmentioning

confidence: 99%

Human activity recognition: suitability of a neuromorphic approach for on-edge AIoT applications

Fra

Forno

Pignari

et al. 2022

Neuromorph. Comput. Eng.

Self Cite

View full text Add to dashboard Cite

Human activity recognition (HAR) is a classification problem involving time-dependent signals produced by body monitoring, and its application domain covers all the aspects of human life, from healthcare to sport, from safety to smart environments. As such, it is naturally well suited for on-edge deployment of personalized point-of-care (POC) analyses or other tailored services for the user. However, typical smart and wearable devices suffer from relevant limitations regarding energy consumption, and this significantly hinders the possibility for successful employment of edge computing for tasks like HAR. In this paper, we investigate how this problem can be mitigated by adopting a neuromorphic approach. By comparing optimized classifiers based on traditional deep neural network (DNN) architectures as well as on recent alternatives like the Legendre Memory Unit (LMU), we show how spiking neural networks (SNNs) can effectively deal with the temporal signals typical of HAR providing high performances at a low energy cost. By carrying out an application-oriented hyperparameter optimization, we also propose a methodology flexible to be extended to different domains, to enlarge the field of neuro-inspired classifier suitable for on-edge artificial intelligence of things (AIoT) applications.

show abstract

“…Besides these popular candidates of non-von Neumann computing a multiplicity of neuromorphic hardware has been developed in the last decade. In Yan et al ( 2021 ), a differentiation in 3 classes is made; (1) systems with static synapses like TrueNorth, NeuroGrid, Braindrop, HiAER-IFAT, DYNAPs, Tianjic, NeuroSoC, and DeepSouth, (2) systems supporting a configurable plasticity like ROLLS, ODIN, and TITAN and lastly, (3) systems supporting a programmable plasticity like both BrainScaleS, both SpiNNaker and Loihi. Another digital representative is focused on memory centric computing is Neurocube (Kim et al, 2016 ).…”

Section: Introductionmentioning

confidence: 99%

“…Very recently, a comparison between Loihi and a prototype of SpiNNaker 2 has been done in Yan et al ( 2021 ). Two kind of benchmark tasks are used, keyword spotting and adaptive robotic control to compare the hardware regarding power consumption and computation time.…”

Section: Introductionmentioning

confidence: 99%

“…In Davies ( 2019 ), an article giving guidance for benchmarking neuromorphic hardware, the temporal wavefront propagation was rated as an interesting candidate by name, as it is seen as a viable contribution to the greater field of neuromorphic benchmarks. While the authors of Yan et al ( 2021 ) include a robotics scenario, their benchmark is limited to neuromorphic hardware. However, to develop efficient robotics solutions with SNNs, it is crucial to know specification- and performance-related details of all accessible systems to make an informed decision regarding hardware.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Benchmarking Highly Parallel Hardware for Spiking Neural Networks in Robotics

et al. 2021

View full text Add to dashboard Cite

Animal brains still outperform even the most performant machines with significantly lower speed. Nonetheless, impressive progress has been made in robotics in the areas of vision, motion- and path planning in the last decades. Brain-inspired Spiking Neural Networks (SNN) and the parallel hardware necessary to exploit their full potential have promising features for robotic application. Besides the most obvious platform for deploying SNN, brain-inspired neuromorphic hardware, Graphical Processing Units (GPU) are well capable of parallel computing as well. Libraries for generating CUDA-optimized code, like GeNN and affordable embedded systems make them an attractive alternative due to their low price and availability. While a few performance tests exist, there has been a lack of benchmarks targeting robotic applications. We compare the performance of a neural Wavefront algorithm as a representative of use cases in robotics on different hardware suitable for running SNN simulations. The SNN used for this benchmark is modeled in the simulator-independent declarative language PyNN, which allows using the same model for different simulator backends. Our emphasis is the comparison between Nest, running on serial CPU, SpiNNaker, as a representative of neuromorphic hardware, and an implementation in GeNN. Beyond that, we also investigate the differences of GeNN deployed to different hardware. A comparison between the different simulators and hardware is performed with regard to total simulation time, average energy consumption per run, and the length of the resulting path. We hope that the insights gained about performance details of parallel hardware solutions contribute to developing more efficient SNN implementations for robotics.

show abstract

Comparing Loihi with a SpiNNaker 2 prototype on low-latency keyword spotting and adaptive robotic control

Cited by 35 publications

References 31 publications

Embodied neuromorphic intelligence

Embodied neuromorphic intelligence

Human activity recognition: suitability of a neuromorphic approach for on-edge AIoT applications

Benchmarking Highly Parallel Hardware for Spiking Neural Networks in Robotics

Contact Info

Product

Resources

About