Using Stochastic Spiking Neural Networks on SpiNNaker to Solve Constraint Satisfaction Problems
@article{FonsecaGuerra2017UsingSS, title={Using Stochastic Spiking Neural Networks on SpiNNaker to Solve Constraint Satisfaction Problems}, author={Gabriel A. Fonseca Guerra and Stephen B. Furber}, journal={Frontiers in Neuroscience}, year={2017}, volume={11} }
Constraint satisfaction problems (CSP) are at the core of numerous scientific and technological applications. However, CSPs belong to the NP-complete complexity class, for which the existence (or not) of efficient algorithms remains a major unsolved question in computational complexity theory. In the face of this fundamental difficulty heuristics and approximation methods are used to approach instances of NP (e.g., decision and hard optimization problems). The human brain efficiently handles…
38 Citations
Solving Constraint Satisfaction Problems Using the Loihi Spiking Neuromorphic Processor
- Computer Science2020 Design, Automation & Test in Europe Conference & Exhibition (DATE)
- 2020
The work in this paper exhibits the first implementation of constraint satisfaction on a low power embedded neuromorphic processor, and aims to show that embedded spiking neuromorphic hardware is capable of executing general problem solving algorithms with great areal and computational efficiency.
Leveraging the Manycore Architecture of the Loihi Spiking Processor to Perform Quasi-Complete Constraint Satisfaction
- Computer Science2020 International Joint Conference on Neural Networks (IJCNN)
- 2020
This work exhibits the first implementation of constraint satisfaction on a low power embedded neuromorphic processor capable of generating a solution set, and shows that embedded spiking neuromorphic hardware is capable parallelizing the constraint satisfaction problem solving process to yield extreme gains in terms of time, power, and energy.
Solving Vertex Cover via Ising Model on a Neuromorphic Processor
- Computer Science2018 IEEE International Symposium on Circuits and Systems (ISCAS)
- 2018
This work demonstrates how a neuromorphic processor can be used to solve the classic vertex cover problem via an Ising spin model and states that space and time efficiency is decreased only by a constant factor without degrading solution quality.
A Neuromorphic Computational Primitive for Robust Context-Dependent Decision Making and Context-Dependent Stochastic Computation
- Computer ScienceIEEE Transactions on Circuits and Systems II: Express Briefs
- 2019
This work presents a mixed-signal analog/digital neuromorphic implementation of a state-dependent SNN architecture that relies on synaptic dis-inhibition to ensure robust decision making even in the face of very large variability in constraint satisfaction problems (CSPs).
A Swarm Optimization Solver Based on Ferroelectric Spiking Neural Networks
- Computer ScienceFront. Neurosci.
- 2019
This work explores the feasibility of connecting Swarm Intelligence and SNN by implementing a generalized SI model on SNN, and demonstrates that such an SI-SNN model is capable of efficiently solving optimization problems, such as parameter optimization of continuous functions and a ubiquitous combinatorial optimization problem, namely, the traveling salesman problem with near-optimal solutions.
PrxCa1−xMnO3 based stochastic neuron for Boltzmann machine to solve “maximum cut” problem
- Computer ScienceAPL Materials
- 2019
The Analog Approximate Sigmoid (AAS) stochastic neuron is proposed to solve the maximum cut—an NP hard problem and the AAS design solves the problem with 98% accuracy, which is comparable with the DPS design but with 10× area and 4× energy advantage.
Accelerated Physical Emulation of Bayesian Inference in Spiking Neural Networks
- Computer ScienceFront. Neurosci.
- 2019
This work presents a spiking network model that performs Bayesian inference through sampling on the BrainScaleS neuromorphic platform, where it is used for generative and discriminative computations on visual data and implicitly demonstrates its robustness to various substrate-specific distortive effects.
Neuromorphic scaling advantages for energy-efficient random walk computations
- Computer ScienceNature Electronics
- 2022
Despite being in an early development stage, it is found that NMC platforms, at a sufficient scale, can drastically reduce the energy demands of high-performance computing (HPC) platforms.
A Spiking Recurrent Neural Network With Phase-Change Memory Neurons and Synapses for the Accelerated Solution of Constraint Satisfaction Problems
- Computer ScienceIEEE Journal on Exploratory Solid-State Computational Devices and Circuits
- 2020
A stochastic spiking neuron based on a phase-change memory (PCM) device for the solution of CSPs within a Hopfield recurrent neural network (RNN).
Neuromorphic scaling advantages for energy-efficient random walk computation
- Computer ScienceArXiv
- 2021
References
SHOWING 1-10 OF 67 REFERENCES
Solving Constraint Satisfaction Problems with Networks of Spiking Neurons
- Computer ScienceFront. Neurosci.
- 2016
It is shown how the energy function of a network of stochastically firing neurons can be shaped in a transparent manner by composing the networks of simple stereotypical network motifs, which enables networks of spiking neurons to produce approximate solutions to difficult constraint satisfaction problems from the domains of planning/optimization and verification/logical inference.
Solving nonlinear optimization problems using networks of spiking neurons
- Computer ScienceProceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium
- 2000
The goal of this paper is to prove that neural networks like the SRM (Spike Response Model) are able to solve nonlinear optimization problems and to demonstrate this for the traveling salesman problem.
“Neural” computation of decisions in optimization problems
- Computer ScienceBiological Cybernetics
- 2004
Results of computer simulations of a network designed to solve a difficult but well-defined optimization problem-the Traveling-Salesman Problem-are presented and used to illustrate the computational power of the networks.
On the Computational Power of Noisy Spiking Neurons
- Computer ScienceNIPS
- 1995
These constructions provide a possible explanation for the fact that biological neural systems can carry out quite complex computations within 100 msec and it turns out that the assumption that these constructions require about the shape of the EPSP's and the behaviour of the noise are surprisingly weak.
The SpiNNaker Project
- Computer ScienceProceedings of the IEEE
- 2014
The current state of the spiking neural network architecture project is reviewed, and the real-time event-driven programming model that supports flexible access to the resources of the machine and has enabled its use by a wide range of collaborators around the world is presented.
SpiNNaker: A 1-W 18-Core System-on-Chip for Massively-Parallel Neural Network Simulation
- Computer ScienceIEEE Journal of Solid-State Circuits
- 2013
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.
Networks of Spiking Neurons: The Third Generation of Neural Network Models
- Computer ScienceElectron. Colloquium Comput. Complex.
- 1996
Networks of spiking neurons: the third generation of neural network models
- Biology, Computer Science
- 1997
Lower Bounds for the Computational Power of Networks of Spiking Neurons
- Computer ScienceNeural Computation
- 1996
It is shown that simple operations on phase differences between spike-trains provide a very powerful computational tool that can in principle be used to carry out highly complex computations on a small network of spiking neurons.
A wafer-scale neuromorphic hardware system for large-scale neural modeling
- Computer Science, BiologyProceedings of 2010 IEEE International Symposium on Circuits and Systems
- 2010
An integrated software/hardware framework has been developed which is centered around a unified neural system description language, called PyNN, that allows the scientist to describe a model and execute it in a transparent fashion on either a neuromorphic hardware system or a numerical simulator.