2020
DOI: 10.1109/tcyb.2018.2871144
|View full text |Cite
|
Sign up to set email alerts
|

Emergent Inference of Hidden Markov Models in Spiking Neural Networks Through Winner-Take-All

Abstract: Hidden Markov Models (HMMs) underpin the solution to many problems in computational neuroscience. However, it is still unclear how to implement inference of HMMs with a network of neurons in the brain. The existing methods suffer from the problem of being non-spiking and inaccurate. Here we build a precise equivalence between the inference equation of HMMs with time-invariant hidden variables and the dynamics of spiking winner-take-all (WTA) neural networks. We show that the membrane potential of each spiking … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
8
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
6
1
1

Relationship

1
7

Authors

Journals

citations
Cited by 20 publications
(8 citation statements)
references
References 49 publications
0
8
0
Order By: Relevance
“…Considering the computing resources and time delay for real-time application, the lightweight model we propose for rapid sleep stage classification maybe more easily adaptable to clinical or wearable devices applications. In future works, we will explore more brain-inspired models (e.g., spiking neural networks) [17], [18] to realize energy-efficient implementation on sleeping scoring tasks.…”
Section: Discussionmentioning
confidence: 99%
“…Considering the computing resources and time delay for real-time application, the lightweight model we propose for rapid sleep stage classification maybe more easily adaptable to clinical or wearable devices applications. In future works, we will explore more brain-inspired models (e.g., spiking neural networks) [17], [18] to realize energy-efficient implementation on sleeping scoring tasks.…”
Section: Discussionmentioning
confidence: 99%
“…Similarly, PGM has also been used to denoise images [167]. Recently, it is shown that PGMs can be implemented by SNNs for various types of computations [53,164,168,169,170,171], thus, when using SNNs for denoising, similar performance can be achieved [107], as illustrated in Fig. 5(D).…”
Section: Modeling the Retina With Snns And Pgmsmentioning
confidence: 95%
“…In Thakur et al (2016) , a hardware implementation of an HMM network has been proposed that utilizes sequential Monte Carlo (SMC) in SNNs. An HMM shown in Figure 8A models a system defined by a process that generates an observable sequence depending on the underlying process ( Yu et al, 2018 ). In an HMM, X t and Y t represent the signal process and the observation, respectively.…”
Section: Bayesian Inference Hardware Implementation With Digital Logic Gatesmentioning
confidence: 99%