Spiking Reservoir Computing for Temporal Edge Intelligence on Loihi

Gaurav, Ramashish; Stewart, Terrence C.; Yi, Yang

doi:10.1109/sec54971.2022.00081

Cited by 3 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternative approaches using reservoir computing paradigms could also be explored due to their largely interconnected neuronal structure mimicking areas of the brain [55]. These architectures have also previously been explored on edge neuromorphic platforms, underpinning their utility [56].…”

Section: Discussionmentioning

confidence: 99%

Simultaneous Velocity and Texture Classification from a Neuromorphic Tactile Sensor Using Spiking Neural Networks

Brayshaw,

Ward-Cherrier,

Pearson

2024

Electronics

View full text Add to dashboard Cite

The neuroTac, a neuromorphic visuo-tactile sensor that leverages the high temporal resolution of event-based cameras, is ideally suited to applications in robotic manipulators and prosthetic devices. In this paper, we pair the neuroTac with Spiking Neural Networks (SNNs) to achieve a movement-invariant neuromorphic tactile sensing method for robust texture classification. Alongside this, we demonstrate the ability of this approach to extract movement profiles from purely tactile data. Our systems achieve accuracies of 95% and 83% across their respective tasks (texture and movement classification). We then seek to reduce the size and spiking activity of our networks with the aim of deployment to edge neuromorphic hardware. This multi-objective optimisation investigation using Pareto frontiers highlights several design trade-offs, where high activity and large network sizes can both be reduced by up to 68% and 94% at the cost of slight decreases in accuracy (8%).

show abstract

Section: Discussionmentioning

confidence: 99%

Simultaneous Velocity and Texture Classification from a Neuromorphic Tactile Sensor Using Spiking Neural Networks

Brayshaw,

Ward-Cherrier,

Pearson

2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Sections 2.3, 3.1.1, 3.2, 4.1, and 5.1 are reused from our previous work. We next lay down our major contributions [contributions from Gaurav et al ( 2022a ) are italicized, rest are novel to this work]:…”

Section: Introductionmentioning

confidence: 99%

“…In our second model with non-linear readout layer, we use this Surrogate Gradient Descent (SurrGD) approach to train it; we provide more details later. Note that this work is an extension of our previous work (Gaurav et al, 2022a) (recently published) where we developed a Spiking Reservoir Computing (SRC) model and deployed it on Loihiin one of the firsts. For the sake of completeness, we present the relevant details of our previous work here.…”

mentioning

confidence: 98%

Reservoir based spiking models for univariate Time Series Classification

Gaurav

Stewart

2023

Front. Comput. Neurosci.

Self Cite

View full text Add to dashboard Cite

A variety of advanced machine learning and deep learning algorithms achieve state-of-the-art performance on various temporal processing tasks. However, these methods are heavily energy inefficient—they run mainly on the power hungry CPUs and GPUs. Computing with Spiking Networks, on the other hand, has shown to be energy efficient on specialized neuromorphic hardware, e.g., Loihi, TrueNorth, SpiNNaker, etc. In this work, we present two architectures of spiking models, inspired from the theory of Reservoir Computing and Legendre Memory Units, for the Time Series Classification (TSC) task. Our first spiking architecture is closer to the general Reservoir Computing architecture and we successfully deploy it on Loihi; the second spiking architecture differs from the first by the inclusion of non-linearity in the readout layer. Our second model (trained with Surrogate Gradient Descent method) shows that non-linear decoding of the linearly extracted temporal features through spiking neurons not only achieves promising results, but also offers low computation-overhead by significantly reducing the number of neurons compared to the popular LSM based models—more than 40x reduction with respect to the recent spiking model we compare with. We experiment on five TSC datasets and achieve new SoTA spiking results (—as much as 28.607% accuracy improvement on one of the datasets), thereby showing the potential of our models to address the TSC tasks in a green energy-efficient manner. In addition, we also do energy profiling and comparison on Loihi and CPU to support our claims.

show abstract

Enhancing SNN Training Performance: A Mixed-Signal Triplet Reconfigurable STDP Circuit with Multiplexing Encoding

Zheng

2023

2023 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

Spiking Reservoir Computing for Temporal Edge Intelligence on Loihi

Cited by 3 publications

References 26 publications

Simultaneous Velocity and Texture Classification from a Neuromorphic Tactile Sensor Using Spiking Neural Networks

Simultaneous Velocity and Texture Classification from a Neuromorphic Tactile Sensor Using Spiking Neural Networks

Reservoir based spiking models for univariate Time Series Classification

Enhancing SNN Training Performance: A Mixed-Signal Triplet Reconfigurable STDP Circuit with Multiplexing Encoding

Contact Info

Product

Resources

About