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

Yu, Zhaofei; Guo, Shangqi; Deng, Feiqi; Yan, Qi; Huang, Keke; Liu, Jian K.; Chen, Feng

doi:10.1109/tcyb.2018.2871144

Cited by 20 publications

(8 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

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%

LightSleepNet: A Lightweight Deep Model for Rapid Sleep Stage Classification with Spectrograms

Zhou

Wang

et al. 2021

2021 43rd Annual International Conference of the IEEE Engineering in Medicine &Amp; Biology Society (EMBC)

View full text Add to dashboard Cite

Deep learning has achieved unprecedented success in sleep stage classification tasks, which starts to pave the way for potential real-world applications. However, due to its enormous size, deployment of deep neural networks is hindered by high cost at various aspects, such as computation power, storage, network bandwidth, power consumption, and hardware complexity. For further practical applications (e.g., wearable sleep monitoring devices), there is a need for simple and compact models. In this paper, we propose a lightweight model, namely LightSleepNet, for rapid sleep stage classification based on spectrograms. Our model is assembled by a much fewer number of model parameters compared to existing ones. Furthermore, we convert the raw EEG data into spectrograms to speed up the training process. We evaluate the model performance on several public sleep datasets with different characteristics. Experimental results show that our lightweight model using spectrogram as input can achieve comparable overall accuracy and Cohen's kappa (SHHS100: 86.7%-81.3%, Sleep-EDF: 83.7%-77.5%, Sleep-EDF-v1: 88.3%-84.5%) compared to the state-of-the-art methods on experimental datasets.

show abstract

Section: Discussionmentioning

confidence: 99%

LightSleepNet: A Lightweight Deep Model for Rapid Sleep Stage Classification with Spectrograms

Zhou

Wang

et al. 2021

2021 43rd Annual International Conference of the IEEE Engineering in Medicine &Amp; Biology Society (EMBC)

View full text Add to dashboard Cite

show abstract

“…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%

Toward the Next Generation of Retinal Neuroprosthesis: Visual Computation with Spikes

Liu

Jia

et al. 2020

Engineering

Self Cite

View full text Add to dashboard Cite

Neuroprosthesis, as one type of precision medicine device, is aiming for manipulating neuronal signals of the brain in a closed-loop fashion, together with receiving stimulus from the environment and controlling some part of our brain/body. In terms of vision, incoming information can be processed by the brain in millisecond interval. The retina computes visual scenes and then sends its output as neuronal spikes to the cortex for further computation. Therefore, the neuronal signal of interest for retinal neuroprosthesis is spike. Closed-loop computation in neuroprosthesis includes two stages: encoding stimulus to neuronal signal, and decoding it into stimulus. Here we review some of the recent progress about visual computation models that use spikes for analyzing natural scenes, including static images and dynamic movies. We hypothesize that for a better understanding of computational principles in the retina, one needs a hypercircuit view of the retina, in which different functional network motifs revealed in the cortex neuronal network should be taken into consideration for the retina. Different building blocks of the retina, including a diversity of cell types and synaptic connections, either chemical synapses or electrical synapses (gap junctions), make the retina an ideal neuronal network to adapt the computational techniques developed in artificial intelligence for modeling of encoding/decoding visual scenes. Altogether, one needs a systems approach of visual computation with spikes to advance the next generation of retinal neuroprosthesis as an artificial visual system.

show abstract

“…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%

Brain-Inspired Hardware Solutions for Inference in Bayesian Networks

Bagheriye

Kwisthout

2021

Front. Neurosci.

View full text Add to dashboard Cite

The implementation of inference (i.e., computing posterior probabilities) in Bayesian networks using a conventional computing paradigm turns out to be inefficient in terms of energy, time, and space, due to the substantial resources required by floating-point operations. A departure from conventional computing systems to make use of the high parallelism of Bayesian inference has attracted recent attention, particularly in the hardware implementation of Bayesian networks. These efforts lead to several implementations ranging from digital circuits, mixed-signal circuits, to analog circuits by leveraging new emerging nonvolatile devices. Several stochastic computing architectures using Bayesian stochastic variables have been proposed, from FPGA-like architectures to brain-inspired architectures such as crossbar arrays. This comprehensive review paper discusses different hardware implementations of Bayesian networks considering different devices, circuits, and architectures, as well as a more futuristic overview to solve existing hardware implementation problems.

show abstract

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

Cited by 20 publications

References 49 publications

LightSleepNet: A Lightweight Deep Model for Rapid Sleep Stage Classification with Spectrograms

LightSleepNet: A Lightweight Deep Model for Rapid Sleep Stage Classification with Spectrograms

Toward the Next Generation of Retinal Neuroprosthesis: Visual Computation with Spikes

Brain-Inspired Hardware Solutions for Inference in Bayesian Networks

Contact Info

Product

Resources

About