paper-with-me

홈 › Papers

A spiking neural algorithm for the Network Flow problem

2019-11-29 · Abdullahi Ali, Johan Kwisthout

It is currently not clear what the potential is of neuromorphic hardware beyond machine learning and neuroscience. In this project, a problem is investigated that is inherently difficult to fully implement in neuromorphic hardware by introducing a new machine model in which a conventional Turing machine and neuromorphic oracle work together to solve such types of problems. We show that the P-complete Max Network Flow problem is intractable in models where the oracle may be consulted only once (create-and-run' model) but becomes tractable using an interactive (neuromorphic co-processor') model of computation. More in specific we show that a logspace-constrained Turing machine with access to an interactive neuromorphic oracle with linear space, time, and energy constraints can solve Max Network Flow. A modified variant of this algorithm is implemented on the Intel Loihi chip; a neuromorphic manycore processor developed by Intel Labs. We show that by off-loading the search for augmenting paths to the neuromorphic processor we can get energy efficiency gains, while not sacrificing runtime resources. This result demonstrates how P-complete problems can be mapped on neuromorphic architectures in a theoretically and potentially practically efficient manner.

📄 PDF Abstract BibTeX arXiv:1911.13097

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Optical Flow Estimation for Spiking Camera

2021-10-08 · CVPR 2022 1 · Liwen Hu, Rui Zhao, Ziluo Ding, Lei Ma 외

As a bio-inspired sensor with high temporal resolution, the spiking camera has an enormous potential in real applications, especially for motion estimation in high-speed scenes. However, frame-based and event-based metho…

Event-based visionMotion EstimationOptical Flow Estimation

SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit Differentiation

2023-08-21 · Malyaban Bal, Abhronil Sengupta

Large language Models (LLMs), though growing exceedingly powerful, comprises of orders of magnitude less neurons and synapses than the human brain. However, it requires significantly more power/energy to operate. In this…

Knowledge DistillationLanguage Modelling

BindsNET: A machine learning-oriented spiking neural networks library in Python

2018-06-04 · Hananel Hazan, Daniel J. Saunders, Hassaan Khan, Darpan T. Sanghavi 외

The development of spiking neural network simulation software is a critical component enabling the modeling of neural systems and the development of biologically inspired algorithms. Existing software frameworks support …

BIG-bench Machine LearningCPUGPUNeural Network simulation+4

Deep Convolutional Spiking Neural Networks for Image Classification

2019-03-28 · Ruthvik Vaila, John Chiasson, Vishal Saxena

Spiking neural networks are biologically plausible counterparts of the artificial neural networks, artificial neural networks are usually trained with stochastic gradient descent and spiking neural networks are trained w…

ClassificationGeneral Classificationimage-classificationImage Classification

Learning flow functions of spiking systems

2023-12-19 · Miguel Aguiar, Amritam Das, Karl H. Johansson

We propose a framework for surrogate modelling of spiking systems. These systems are often described by stiff differential equations with high-amplitude oscillations and multi-timescale dynamics, making surrogate models …