A Bio-Inspired Hierarchical Spiking Neural Network With Reward-Modulated STDP Learning Rule for AER Object Recognition

Zhou, Qian; Li, Xiaohu

doi:10.1109/jsen.2022.3189679

Cited by 9 publications

(8 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also compare the performance of our proposed method in this paper with Liu’s 32 method and Zhou’s 30 method that used SNN to make classification. In Liu’s 32 method, primary features of event streams were extracted using 16 Gabor filters of different orientations and scales in the event-driven convolution.…”

Section: Resultsmentioning

confidence: 99%

“…The extracted features were fed into a four-layer unsupervised spiking CNN with STDP rules for classification and recognition. Zhou et al 30 also used event-driven convolution with different Gabor filters to extract primary features and they used SNN with R-STDP learning rule to further extracting features and make classification. The structure of SNN is the same with our method.…”

Section: Baseline Methodsmentioning

confidence: 99%

“…The reliable feature extraction capability of Gabor filters also encouraged subsequent Liu et al 28 . and Zhou et al 30 . to directly use them as the front-end of feature coding.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Event camera object recognition using spatiotemporal event time surface and reward-modulated spike-timing-dependent plasticity learning rule

Zhou,

Zhang

2024

J. Electron. Imag.

Self Cite

View full text Add to dashboard Cite

Event cameras record moving objects with asynchronous event streams. It remains a challenge to make full use of the spatiotemporal information of event streams to extract high-quality features and to make event camera object recognition. We propose an event-based event camera object recognition system, which includes a denoising module and an object recognition module. The denoising module removes noise events using spatiotemporal information of the events. The object recognition module extracts primary spatiotemporal features based on the event time surface prototypes obtained by clustering, then further extracts complex diagnostic features, and makes object recognition using spiking neural networks with reward-modulated spike-timing-dependent plasticity learning rule. Experimental results demonstrate that our system has better performance than baseline methods on five popular event camera datasets, especially on datasets with rich spatiotemporal dynamics. Our denoising method improves the noise robustness of our event camera object recognition system on high-speed moving datasets that are greatly affected by noises. Moreover, our method has much better recognition ability than baseline methods when using short input event streams. Our method is very beneficial for developing event-based event camera object recognition algorithm when event streams are short or noises are serious.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Baseline Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Event camera object recognition using spatiotemporal event time surface and reward-modulated spike-timing-dependent plasticity learning rule

Zhou,

Zhang

2024

J. Electron. Imag.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Currently, improved STDP learning rules include event-driven STDP rules and adaptive threshold-based STDP rules. [143] Furthermore, to improve the performance of SNN on classification tasks, the convolutional network is combined with the SNN network, which can increase the depth of layers of spike convolution. [144] ReSuMe proposes a supervised algorithm to learn the complex spatiotemporal patterns of spike sequences.…”

Section: Learning Rules For Spiking Networkmentioning

confidence: 99%

Integrated Memristor Network for Physiological Signal Processing

Cai

Yue

et al. 2023

Adv Elect Materials

View full text Add to dashboard Cite

Humans are complex organisms made by millions of physiological systems. Therefore, physiological activities can represent physical or mental states of the human body. Physiological signal processing is essential in monitoring human physiological features. For example, non‐invasive electroencephalography (EEG) signals can be used to reconstruct brain consciousness and detect eye movements for identity verification. However, physiological signal processing requires high resolution, high sensitivity, fast responses, and low power consumption, hindering practical hardware design for physiological signal processing. The bionic capability of memristor devices is very promising in the context of building physiological signal processing hardware and they have demonstrated a handful of advantages over the traditional Von Neumann architecture system in accelerating neural networks. Memristor networks can be integrated as a hardware system for physiological signal processing that can deliver higher energy efficiency and lower latency compared to traditional implementations. This review paper first introduces memristor characteristics, followed by a comprehensive literature study of memristor‐based networks. Physiology signal processing applications enabled by these integrated memristor networks are also presented in this review. In summary, this paper aims to provide a new perspective on physiological signal processing using integrated memristor networks.

show abstract

“…In the human brain, information transmission, memory, and preprocessing can occur simultaneously in a single cell–synapse, which relies on the updating mechanism of synaptic weight ( w ). − One important weight update mechanism is STDP, which reveals that the synapses increase or decrease their transmitting and memory ability exponentially depending on the spike timing difference (Δ t = t pre – t post ) between the presynaptic and postsynaptic spikes. − The STDP is not only a general learning rule but also has received attention in application-based contexts. This mechanism is widely used in neuromorphic circuits to accelerate calculate to realize pulse timing detection, information learning and recognitions, − data classifications, and directional selectivity …”

Section: Introductionmentioning

confidence: 99%

All-Fiber Synapse Utilizing Phase Change Materials for Information Recognition and Processing

Li,

Zhang,

Liu

et al. 2023

ACS Photonics

View full text Add to dashboard Cite

Optical fiber has been widely used in telecommunication networks due to its inherent advantages of considerable bandwidth and ultrahigh-speed light transmission. However, it only serves as the transmission medium and cannot identify and process data directly in the fiber. One solution is to simulate neuromorphic functions directly in fibers. Here, Ge 2 Sb 2 Te 5 -assisted all-fiber synapses are proposed for information recognition and processing. The synaptic spike-timing-dependent plasticity, an important synaptic learning rule in Hebbian theory, can be mimicked by controlling the taper extension of the tapered fiber and integrating Ge 2 Sb 2 Te 5 on its waist. The designed all-fiber synapse interacts efficiently with Ge 2 Sb 2 Te 5 to alter light transmission, expressed as the synaptic weight. This synapse exhibits 10-level weight, 22% transmission contrast ratio, and 180 ns fast switching time for a single pulse. Additionally, the character recognition and arithmetic operation functions are demonstrated based on the proposed all-fiber synapses, inspiring a new paradigm for in-fiber processing.

show abstract

A Bio-Inspired Hierarchical Spiking Neural Network With Reward-Modulated STDP Learning Rule for AER Object Recognition

Cited by 9 publications

References 69 publications

Event camera object recognition using spatiotemporal event time surface and reward-modulated spike-timing-dependent plasticity learning rule

Event camera object recognition using spatiotemporal event time surface and reward-modulated spike-timing-dependent plasticity learning rule

Integrated Memristor Network for Physiological Signal Processing

All-Fiber Synapse Utilizing Phase Change Materials for Information Recognition and Processing

Contact Info

Product

Resources

About