Analyzing time-to-first-spike coding schemes: A theoretical approach

Bonilla, Lina; Gautrais, Jacques; Thorpe, Simon J.; Masquelier, Timothée

doi:10.3389/fnins.2022.971937

Cited by 16 publications

(11 citation statements)

References 28 publications

(48 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These models take the form of artificial spiking neural networks (SNNs) and have been able to demonstrate their practical applications for image categorization [39]. One of these is the SpikeNet algorithm, which uses a purely temporal approach by encoding information using one spike per neuron by using the rank of neurons' activation [38,40]. Another class of artificial SNNs use precise spike timing as a metric in order to determine the structure of the network in order to minimize a cost function.…”

Section: How Precise Spike Timing May Encode Vectors Of Real Valuesmentioning

confidence: 99%

Precise Spiking Motifs in Neurobiological and Neuromorphic Data

Grimaldi¹,

Gruel²,

Besnainou³

et al. 2022

Preprint

View full text Add to dashboard Cite

Why do neurons communicate through spikes? By definition, spikes are all-or-none neural events which occur at continuous times. In other words, spikes are on one side binary, existing or not without further details, and on the other can occur at any asynchronous time, without the need for a centralized clock. This stands in stark contrast to the analog representation of values and the discretized timing classically used in digital processing and at the base of modern-day neural networks. As neural systems almost systematically use this so-called event-based representation in the living world, a better understanding of this phenomenon remains a fundamental challenge in neurobiology in order to better interpret the profusion of recorded data. With the growing need for intelligent embedded systems, it also emerges as a new computing paradigm to enable the efficient operation of a new class of sensors and event-based computers, called neuromorphic, which could enable significant gains in computation time and energy consumption — a major societal issue in the era of the digital economy and global warming. In this review paper, we provide evidence from biology, theory and engineering that the precise timing of spikes plays a crucial role in our understanding of the efficiency of neural networks.

show abstract

Section: How Precise Spike Timing May Encode Vectors Of Real Valuesmentioning

confidence: 99%

Precise Spiking Motifs in Neurobiological and Neuromorphic Data

Grimaldi¹,

Gruel²,

Besnainou³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…A timing-based learning method is a method that focuses on the displacement of the spike time [28]. The coding most commonly used in this learning method is time-to-first-spike (TTFS) coding, which has the property that each neuron fires at most once [29,30]. Because the information is contained in the timing of a single spike and the gradient is computed directly using the spike timing, this coding is expected to realize an ideal temporal coding.…”

Section: Introductionmentioning

confidence: 99%

Sparse-Firing Regularization Methods for Spiking Neural Networks with Time-to-First-Spike Coding

Sakemi,

Yamamoto,

Hosomi

et al. 2023

Preprint

View full text Add to dashboard Cite

The training of multilayer spiking neural networks (SNNs) using the error backpropagation algorithm has made significant progress in recent years. Among the various training schemes, the error backpropagation method that directly uses the firing time of neurons has attracted considerable attention because it can realize ideal temporal coding. This method uses time-to-first-spike (TTFS) coding, in which each neuron fires at most once, and this restriction on the number of firings enables information to be processed at a very low firing frequency. This low firing frequency increases the energy efficiency of information processing in SNNs. However, only an upper limit has been provided for TTFS-coded SNNs, and the information-processing capability of SNNs at lower firing frequencies has not been fully investigated. In this paper, we propose two spike-timing-based sparse-firing (SSR) regularization methods to further reduce the firing frequency of TTFS-coded SNNs. Both methods are characterized by the fact that they only require information about the firing timing and associated weights. The effects of these regularization methods were investigated on the MNIST, Fashion-MNIST, and CIFAR-10 datasets using multilayer perceptron networks and convolutional neural network structures.

show abstract

“…In particular, the first spike after a stimulus (Panzeri et al, 2001 ; Johansson and Birznieks, 2004 ) is capable of reliably conveying considerable information. This inspired methods based on the time-to-first-spike (TTFS) coding, resulting in fewer spikes and efficient computation (Bonilla et al, 2022 ; Yu et al, 2023 ). In practice, most of these methods force each neuron to fire at most one spike (Mostafa, 2018 ; Kheradpisheh and Masquelier, 2020 ; Göltz et al, 2021 ; Mirsadeghi et al, 2021 ; Zhou et al, 2021 ; Comşa et al, 2022 ) or assume there is a very long refractory period after a spike (Kotariya and Ganguly, 2021 ) to allow the computation of exact derivatives of postsynaptic spike times with respect to presynaptic times.…”

Section: Introductionmentioning

confidence: 99%

First-spike coding promotes accurate and efficient spiking neural networks for discrete events with rich temporal structures

Liu,

Leung,

Dragotti

2023

Front. Neurosci.

View full text Add to dashboard Cite

Spiking neural networks (SNNs) are well-suited to process asynchronous event-based data. Most of the existing SNNs use rate-coding schemes that focus on firing rate (FR), and so they generally ignore the spike timing in events. On the contrary, methods based on temporal coding, particularly time-to-first-spike (TTFS) coding, can be accurate and efficient but they are difficult to train. Currently, there is limited research on applying TTFS coding to real events, since traditional TTFS-based methods impose one-spike constraint, which is not realistic for event-based data. In this study, we present a novel decision-making strategy based on first-spike (FS) coding that encodes FS timings of the output neurons to investigate the role of the first-spike timing in classifying real-world event sequences with complex temporal structures. To achieve FS coding, we propose a novel surrogate gradient learning method for discrete spike trains. In the forward pass, output spikes are encoded into discrete times to generate FS times. In the backpropagation, we develop an error assignment method that propagates error from FS times to spikes through a Gaussian window, and then supervised learning for spikes is implemented through a surrogate gradient approach. Additional strategies are introduced to facilitate the training of FS timings, such as adding empty sequences and employing different parameters for different layers. We make a comprehensive comparison between FS and FR coding in the experiments. Our results show that FS coding achieves comparable accuracy to FR coding while leading to superior energy efficiency and distinct neuronal dynamics on data sequences with very rich temporal structures. Additionally, a longer time delay in the first spike leads to higher accuracy, indicating important information is encoded in the timing of the first spike.

show abstract

Analyzing time-to-first-spike coding schemes: A theoretical approach

Cited by 16 publications

References 28 publications

Precise Spiking Motifs in Neurobiological and Neuromorphic Data

Precise Spiking Motifs in Neurobiological and Neuromorphic Data

Sparse-Firing Regularization Methods for Spiking Neural Networks with Time-to-First-Spike Coding

First-spike coding promotes accurate and efficient spiking neural networks for discrete events with rich temporal structures

Contact Info

Product

Resources

About