• Corpus ID: 85518216

Spike-based primitives for graph algorithms

@article{Hamilton2019SpikebasedPF,
  title={Spike-based primitives for graph algorithms},
  author={Kathleen E. Hamilton and Tiffany M. Mintz and Catherine D. Schuman},
  journal={ArXiv},
  year={2019},
  volume={abs/1903.10574}
}
In this paper we consider graph algorithms and graphical analysis as a new application for neuromorphic computing platforms. We demonstrate how the nonlinear dynamics of spiking neurons can be used to implement low-level graph operations. Our results are hardware agnostic, and we present multiple versions of routines that can utilize static synapses or require synapse plasticity. 

Figures and Tables from this paper

Dynamic Programming with Spiking Neural Computing

TLDR
It is demonstrated that a broad class of combinatorial and graph problems known as dynamic programs enjoy simple and efficient neuromorphic implementations, by developing a general technique to convert dynamic programs to spiking neuromorphic algorithms.

Provable Advantages for Graph Algorithms in Spiking Neural Networks

TLDR
This work presents a theoretical framework for designing and assessing the performance of algorithms executing in networks consisting of spiking artificial neurons, and proves a polynomial-factor advantage even when an SNN consisting of a simple grid-like network of neurons.

Shortest Path and Neighborhood Subgraph Extraction on a Spiking Memristive Neuromorphic Implementation

TLDR
This work demonstrates two graph problems that can be solved using SNCs and discusses the approach for mapping these applications to an SNC, and estimates the performance of a memristive SNC for these applications on three real-world graphs.

Neuromorphic Graph Algorithms: Cycle Detection, Odd Cycle Detection, and Max Flow

TLDR
This paper presents a neuromorphic implementation of cycle detection, odd cycle Detection, and the Ford-Fulkerson max-flow algorithm, and shows that within the neuromorphic implementations early stopping criteria can be implemented to further improve performance.

SpikE: spike-based embeddings for multi-relational graph data

  • D. DoldJ. Garrido
  • Computer Science
    2021 International Joint Conference on Neural Networks (IJCNN)
  • 2021
TLDR
A spike-based algorithm where nodes in a graph are represented by single spike times of neuron populations and relations as spike time differences between populations is proposed, compatible with recently proposed frameworks for training spiking neural networks.

Neuro-symbolic computing with spiking neural networks

TLDR
This work extends previous work on spike-based graph algorithms by demonstrating how symbolic and multi-relational information can be encoded using spiking neurons, allowing reasoning over symbolic structures like knowledge graphs with spiking neural networks.

Composing neural algorithms with Fugu

TLDR
The Fugu framework is designed to provide a higher level abstraction as a hardware-independent mechanism for linking a variety of scalable spiking neural algorithms fromA variety of sources to provide sophisticated processing through compositionality.

Neuromorphic Graph Algorithms: Extracting Longest Shortest Paths and Minimum Spanning Trees

TLDR
This work proposes a preprocessing technique that introduces fractional offsets on the synaptic delays of neuromorphic graphs in order to break ties, which enables two graph algorithms: longest shortest path extraction and minimum spanning trees.

Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook

TLDR
This survey reviews results that are obtained to date with Loihi across the major algorithmic domains under study, including deep learning approaches and novel approaches that aim to more directly harness the key features of spike-based neuromorphic hardware.

Caspian: A Neuromorphic Development Platform

TLDR
Caspian offers a high-level API along with a fast spiking simulator to enable the rapid development of neuromorphic solutions and an FPGA architecture that allows for simplified deployment -- particularly in SWaP constrained environments.

References

SHOWING 1-10 OF 21 REFERENCES

Non-Neural Network Applications for Spiking Neuromorphic Hardware

TLDR
Growing research showing the viability of ultra-low-power neural accelerators as co-processors for classic compute algorithms, such as random walk simulations and graph is discussed.

Shortest Path and Neighborhood Subgraph Extraction on a Spiking Memristive Neuromorphic Implementation

TLDR
This work demonstrates two graph problems that can be solved using SNCs and discusses the approach for mapping these applications to an SNC, and estimates the performance of a memristive SNC for these applications on three real-world graphs.

Spiking spin-glass models for label propagation and community detection

TLDR
This paper presents a method of community detection using label propagation in undirected, unweighted graphs which incorporates elements of neural computing and spike-based data and presents it as a candidate for a split-computing workflow that incorporates neuromorphic hardware and does not require extensive pre-training of network parameters.

Spiking network algorithms for scientific computing

TLDR
A number of algorithms exemplifying concepts central to spiking networks including spike timing and synaptic delay are demonstrated and the application of cross-correlation particle image velocimetry is discussed.

Spiking Neural Algorithms for Markov Process Random Walk

TLDR
Two neural algorithms that can be used to efficiently implement random walks on spiking neuromorphic hardware are considered and their ability to model random walkers under different probabilistic conditions are illustrated.

A million spiking-neuron integrated circuit with a scalable communication network and interface

TLDR
Inspired by the brain’s structure, an efficient, scalable, and flexible non–von Neumann architecture is developed that leverages contemporary silicon technology and is well suited to many applications that use complex neural networks in real time, for example, multiobject detection and classification.

Spiking Neuron Models: Single Neurons, Populations, Plasticity

TLDR
A comparison of single and two-dimensional neuron models for spiking neuron models and models of Synaptic Plasticity shows that the former are superior to the latter, while the latter are better suited to population models.

Loihi: A Neuromorphic Manycore Processor with On-Chip Learning

TLDR
Loihi is a 60-mm2 chip fabricated in Intels 14-nm process that advances the state-of-the-art modeling of spiking neural networks in silicon, and can solve LASSO optimization problems with over three orders of magnitude superior energy-delay-product compared to conventional solvers running on a CPU iso-process/voltage/area.

SpiNNaker: A 1-W 18-Core System-on-Chip for Massively-Parallel Neural Network Simulation

TLDR
The design requirements for the very demanding target application, the SpiNNaker micro-architecture, are reviewed and the chips are fully operational and meet their power and performance requirements.

Neuromorphic computing using non-volatile memory

TLDR
The relevant virtues and limitations of these devices are assessed, in terms of properties such as conductance dynamic range, (non)linearity and (a)symmetry of conductance response, retention, endurance, required switching power, and device variability.