Learning with Precise Spike Times: A New Decoding Algorithm for Liquid State Machines

Florescu, Dorian; Coca, Daniel

doi:10.1162/neco_a_01218

Cited by 6 publications

(3 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A high-precision numerical solution is important to ensure that the network dynamics can function correctly and the network can capture precise temporal information to learn complex spatiotemporal sequences or features. Moreover, a liquid state machine (LSM) network is a type of biological SNN with a high computational capability to solve different spatio-temporal tasks [56]. It also uses precise spike timing to process information.…”

Section: B Impact Of Rk3 Methods On Scalabilitymentioning

confidence: 99%

Toward the Optimal Design and FPGA Implementation of Spiking Neural Networks

Guo

Yantır

Fouda

et al. 2022

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

The performance of a biologically plausible spiking neural network (SNN) largely depends on the model parameters and neural dynamics. This paper proposes a parameter optimization scheme for improving the performance of a biologically plausible SNN and a parallel on-FPGA online learning neuromorphic platform for the digital implementation based on two numerical methods, namely Euler and the 3rd-order Runge-Kutta (RK3) methods. The optimization scheme explores the impact of biological time constants on information transmission in the SNN and improves the convergence rate of the SNN on digit recognition with a suitable choice of the time constants. The parallel digital implementation leads to a significant speedup over software simulation on a general-purpose CPU. The parallel implementation with Euler method enables around 180× (20×) training (inference) speedup over a Pytorch-based SNN simulation on CPU. Moreover, compared with previous work, our parallel implementation shows more than 300× (240×) improvement on speed and 180×(250×) reduction on energy consumption for training (inference). In addition, due to the highorder accuracy, RK3 method is demonstrated to gain 2× training speedup over Euler method, which makes it suitable for online training in real-time applications.

show abstract

Section: B Impact Of Rk3 Methods On Scalabilitymentioning

confidence: 99%

Toward the Optimal Design and FPGA Implementation of Spiking Neural Networks

Guo

Yantır

Fouda

et al. 2022

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

show abstract

“…The LSM model in [21] is trained by the recursive least square method using liquid filtered output. It results in the loss of the accurate spike time information produced by the liquid neuron [22]. In this work, readout neurons are trained by the ReSuMe algorithm [23,24].…”

Section: Proposed Methodsmentioning

confidence: 99%

Breast Cancer Recognition Using Saliency-Based Spiking Neural Network

Dong

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The spiking neural networks (SNNs) use event-driven signals to encode physical information for neural computation. SNN takes the spiking neuron as the basic unit. It modulates the process of nerve cells from receiving stimuli to firing spikes. Therefore, SNN is more biologically plausible. Although the SNN has more characteristics of biological neurons, SNN is rarely used for medical image recognition due to its poor performance. In this paper, a reservoir spiking neural network is used for breast cancer image recognition. Due to the difficulties of extracting the lesion features in medical images, a salient feature extraction method is used in image recognition. The salient feature extraction network is composed of spiking convolution layers, which can effectively extract the features of lesions. Two temporal encoding manners, namely, linear time encoding and entropy-based time encoding methods, are used to encode the input patterns. Readout neurons use the ReSuMe algorithm for training, and the Fruit Fly Optimization Algorithm (FOA) is employed to optimize the network architecture to further improve the reservoir SNN performance. Three modality datasets are used to verify the effectiveness of the proposed method. The results show an accuracy of 97.44% for the BreastMNIST database. The classification accuracy is 98.27% on the mini-MIAS database. And the overall accuracy is 95.83% for the BreaKHis database by using the saliency feature extraction, entropy-based time encoding, and network optimization.

show abstract

“…Consequently, sequence {t k } k∈Z is called a spike train, where the spike refers to the firing of an action potential, representing the information transmission method in the mammalian cortex. Previously, the IF model was used for system identification of biological neurons [14,15] to perform machine learning tasks [16,17] but also for input reconstruction [13,[18][19][20][21]. The IF model adds input g(t) with bias parameter b, and subsequently integrates the output to generate a strictly increasing function y(t).…”

Section: Time Encodingmentioning

confidence: 99%

Signal Filtering Using Neuromorphic Measurements

Florescu,

Coca

2023

JLPEA

Self Cite

View full text Add to dashboard Cite

Digital filtering is a fundamental technique in digital signal processing, which operates on a digital sequence without any information on how the sequence was generated. This paper proposes a methodology for designing the equivalent of digital filtering for neuromorphic samples, which are a low-power alternative to conventional digital samples. In the literature, filtering using neuromorphic samples is performed by filtering the reconstructed analog signal, which is required to belong to a predefined input space. We show that this requirement is not necessary, and introduce a new method for computing the neuromorphic samples of the filter output directly from the input samples, backed by theoretical guarantees. We show numerically that we can achieve a similar accuracy compared to that of the conventional method. However, given that we bypass the analog signal reconstruction step, our results show significantly reduced computation time for the proposed method and good performance even when signal recovery is not possible.

show abstract

Learning with Precise Spike Times: A New Decoding Algorithm for Liquid State Machines

Cited by 6 publications

References 51 publications

Toward the Optimal Design and FPGA Implementation of Spiking Neural Networks

Toward the Optimal Design and FPGA Implementation of Spiking Neural Networks

Breast Cancer Recognition Using Saliency-Based Spiking Neural Network

Signal Filtering Using Neuromorphic Measurements

Contact Info

Product

Resources

About