An Online Unsupervised Structural Plasticity Algorithm for Spiking Neural Networks

Roy, Subhrajit; Basu, Arindam

doi:10.1109/tnnls.2016.2582517

Cited by 33 publications

(27 citation statements)

References 35 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Finally, we hypothesize that the retinal circuit has a computational network unit as winner-take-all (WTA) motif. In the cortical cortex, WTA circuit has been suggested as a powerful computational network motif to implement normalization [49], visual attention [50], classification [51], and others [52].…”

Section: Winner-take-all Networkmentioning

confidence: 99%

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

Liu

Jia

et al. 2020

Engineering

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

Section: Winner-take-all Networkmentioning

confidence: 99%

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

Liu

Jia

et al. 2020

Engineering

View full text Add to dashboard Cite

show abstract

“…WTA circuit has been suggested as a ubiquitous motif of cortical microcircuits [31], which is widely used to implement normalization [32], visual attention [33] and classification [34]. We consider a WTA circuit of K output spiking neurons (blue triangles) z 1 , .…”

Section: B Winner-take-all Circuitmentioning

confidence: 99%

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

Guo

Deng

et al. 2020

IEEE Trans. Cybern.

View full text Add to dashboard Cite

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 neuron in the WTA circuit encodes the logarithm of the posterior probability of the hidden variable in each state, and the firing rate of each neuron is proportional to the posterior probability of the HMMs. We prove that the time course of neural firing rate can implement posterior inference of HMMs. Theoretical analysis and experimental results show that the proposed WTA circuit can get accurate inference results of HMMs.

show abstract

“…However, SNN can only receive discrete spike signals as network inputs, thus the image data needs to be first converted into spike signals by certain rules. In this paper, Poisson-distributed spike encoding [18], [27] is used to produce spikes for SNN input.…”

Section: A Test Datasetsmentioning

confidence: 99%

Self-Evolutionary Neuron Model for Fast-Response Spiking Neural Networks

Zhang¹,

Niu²,

Gao³

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

An Online Unsupervised Structural Plasticity Algorithm for Spiking Neural Networks

Cited by 33 publications

References 35 publications

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

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

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

Self-Evolutionary Neuron Model for Fast-Response Spiking Neural Networks

Contact Info

Product

Resources

About