Spike-based graph centrality measures

Hamilton, Kathleen E.; Mintz, Tiffany M.; Date, Prasanna; Schuman, Catherine D.

doi:10.1145/3407197.3407199

Cited by 17 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each synapse multiplies the incoming signal (spike) by its weight, stalls for a time denoted by its delay, and deposits the signal into its postsynaptic neuron. Several applications leverage this model of neuromorphic computing in the literature, including neuromorphic graph algorithms (Kay et al, 2020(Kay et al, , 2021Hamilton et al, 2020b), sparse binary matrix multiplication (Schuman et al, 2021), spiking graph neural networks (Cong et al, 2022), autonomous vehicles (Patton et al, 2021), epidemiological simulations (Hamilton et al, 2020a), classifying supercomputer failures (Date et al, 2018), and many others (Aimone et al, 2022).…”

Section: Algorithmsmentioning

confidence: 99%

Abisko: Deep codesign of an architecture for spiking neural networks using novel neuromorphic materials

Vetter

Date

Fahim

et al. 2023

The International Journal of High Performance Computing Applica

Self Cite

View full text Add to dashboard Cite

The Abisko project aims to develop an energy-efficient spiking neural network (SNN) computing architecture and software system capable of autonomous learning and operation. The SNN architecture explores novel neuromorphic devices that are based on resistive-switching materials, such as memristors and electrochemical RAM. Equally important, Abisko uses a deep codesign approach to pursue this goal by engaging experts from across the entire range of disciplines: materials, devices and circuits, architectures and integration, software, and algorithms. The key objectives of our Abisko project are threefold. First, we are designing an energy-optimized high-performance neuromorphic accelerator based on SNNs. This architecture is being designed as a chiplet that can be deployed in contemporary computer architectures and we are investigating novel neuromorphic materials to improve its design. Second, we are concurrently developing a productive software stack for the neuromorphic accelerator that will also be portable to other architectures, such as field-programmable gate arrays and GPUs. Third, we are creating a new deep codesign methodology and framework for developing clear interfaces, requirements, and metrics between each level of abstraction to enable the system design to be explored and implemented interchangeably with execution, measurement, a model, or simulation. As a motivating application for this codesign effort, we target the use of SNNs for an analog event detector for a high-energy physics sensor.

show abstract

Section: Algorithmsmentioning

confidence: 99%

Abisko: Deep codesign of an architecture for spiking neural networks using novel neuromorphic materials

Vetter

Date

Fahim

et al. 2023

The International Journal of High Performance Computing Applica

Self Cite

View full text Add to dashboard Cite

show abstract

“…CoNNTrA is not restricted to binary or ternary learning parameters specifically, but can train any configuration of learning parameters as long as they are finite and discrete. We believe CoNNTrA would be able to train deep neural networks having low error, low memory and low power for edge computing systems in the post Moore's law era, especially when combined with neuromorphic computing systems, which are known to be resilient and energy efficient [20], and have a wide range of applications such as graph algorithms [21], [22], modeling epidemics [23] and predicting supercomputer failures [24].…”

Section: Related Workmentioning

confidence: 99%

Training Deep Neural Networks with Constrained Learning Parameters

Date,

Carothers,

Mitchell

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Today's deep learning models are primarily trained on CPUs and GPUs. Although these models tend to have low error, they consume high power and utilize large amount of memory owing to double precision floating point learning parameters. Beyond the Moore's law, a significant portion of deep learning tasks would run on edge computing systems, which will form an indispensable part of the entire computation fabric. Subsequently, training deep learning models for such systems will have to be tailored and adopted to generate models that have the following desirable characteristics: low error, low memory, and low power. We believe that deep neural networks (DNNs), where learning parameters are constrained to have a set of finite discrete values, running on neuromorphic computing systems would be instrumental for intelligent edge computing systems having these desirable characteristics. To this extent, we propose the Combinatorial Neural Network Training Algorithm (CoNNTrA), that leverages a coordinate gradient descent-based approach for training deep learning models with finite discrete learning parameters. Next, we elaborate on the theoretical underpinnings and evaluate the computational complexity of CoNNTrA. As a proof of concept, we use CoNNTrA to train deep learning models with ternary learning parameters on the MNIST, Iris and ImageNet data sets and compare their performance to the same models trained using Backpropagation. We use following performance metrics for the comparison: (i) Training error; (ii) Validation error; (iii) Memory usage; and (iv) Training time. Our results indicate that CoNNTrA models use 32× less memory and have errors at par with the Backpropagation models.

show abstract

“…Recently, there exists some works of combining SNNs with graphic scenarios, whereas these studies mainly focused on applying graph theory to analyze the features of spiking neuron and network topology [Piekniewski, 2007;Cancan, 2019;Jovanović and Rotter, 2016], or using the features of spiking neurons to solve simple graph-related problems, such as the shortest path problems, clustering problems, minimal spanning tree problems [Sala and Cios, 1999;Hamilton et al, 2020]. More recently, the work [Gu et al, 2020] introduced a graph convolution to pre-process tactile data and trained an SNN classifier.…”

Section: Introductionmentioning

confidence: 99%

Exploiting Spiking Dynamics with Spatial-temporal Feature Normalization in Graph Learning

Deng

et al. 2021

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

Biological spiking neurons with intrinsic dynamics underlie the powerful representation and learning capabilities of the brain for processing multimodal information in complex environments. Despite recent tremendous progress in spiking neural networks (SNNs) for handling Euclidean-space tasks, it still remains challenging to exploit SNNs in processing non-Euclidean-space data represented by graph data, mainly due to the lack of effective modeling framework and useful training techniques. Here we present a general spike-based modeling framework that enables the direct training of SNNs for graph learning. Through spatial-temporal unfolding for spiking data flows of node features, we incorporate graph convolution filters into spiking dynamics and formalize a synergistic learning paradigm. Considering the unique features of spike representation and spiking dynamics, we propose a spatial-temporal feature normalization (STFN) technique suitable for SNN to accelerate convergence. We instantiate our methods into two spiking graph models, including graph convolution SNNs and graph attention SNNs, and validate their performance on three node-classification benchmarks, including Cora, Citeseer, and Pubmed. Our model can achieve comparable performance with the state-of-the-art graph neural network (GNN) models with much lower computation costs, demonstrating great benefits for the execution on neuromorphic hardware and prompting neuromorphic applications in graphical scenarios.

show abstract

Spike-based graph centrality measures

Cited by 17 publications

References 22 publications

Abisko: Deep codesign of an architecture for spiking neural networks using novel neuromorphic materials

Abisko: Deep codesign of an architecture for spiking neural networks using novel neuromorphic materials

Training Deep Neural Networks with Constrained Learning Parameters

Exploiting Spiking Dynamics with Spatial-temporal Feature Normalization in Graph Learning

Contact Info

Product

Resources

About