Event Camera Data Classification Using Spiking Networks with Spike-Timing-Dependent Plasticity

Safa, Ali; Ocket, Ilia; Bourdoux, André; Sahli, Hichem; Catthoor, Francky; Gielen, Georges

doi:10.1109/ijcnn55064.2022.9892362

Cited by 9 publications

(3 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This situation is even more challenging for the colored image dataset CIFAR-10 [58] and more difficult CIFAR10-DVS [59]. These datasets require several layers of convolutional spiking neural networks to achieve high performance [60] [61]. CDNA-SNN with fully connected layers did not achieve comparable results to state-ofthe-art convolutional SNNs on these datasets.…”

Section: Discussionmentioning

confidence: 99%

CDNA-SNN: A New Spiking Neural Network for Pattern Classification Using Neuronal Assemblies

Saranirad,

Dora,

McGinnity

et al. 2024

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

Spiking neural networks (SNNs) mimic their biological counterparts more closely than their predecessors and are considered the third generation of artificial neural networks. It has been proven that networks of spiking neurons have a higher computational capacity and lower power requirements than sigmoidal neural networks. This paper introduces a new type of spiking neural network that draws inspiration and incorporates concepts from neuronal assemblies in the human brain. The proposed network, termed as CDNA-SNN, assigns each neuron learnable values known as Class-Dependent Neuronal Activations (CDNAs) which indicate the neuron's average relative spiking activity in response to samples from different classes. A new learning algorithm that categorizes the neurons into different class assemblies based on their CDNAs is also presented. These neuronal assemblies are trained via a novel training method based on Spike-Timing Dependent Plasticity (STDP) to have high activity for their associated class and low firing rate for other classes. Also, using CDNAs, a new type of STDP that controls the amount of plasticity based on the assemblies of pre-and postsynaptic neurons is proposed. The performance of CDNA-SNN is evaluated on five datasets from the UCI machine learning repository, as well as MNIST and Fashion MNIST, using nested cross-validation for hyperparameter optimization. Our results show that CDNA-SNN significantly outperforms SWAT (p<0.0005) and SpikeProp (p<0.05) on 3/5 and SRESN (p<0.05) on 2/5 UCI datasets while using the significantly lower number of trainable parameters. Furthermore, compared to other supervised, fully connected SNNs, the proposed SNN reaches the best performance for Fashion MNIST and comparable performance for MNIST and N-MNIST, also utilizing much less (1-35%) parameters.

show abstract

Section: Discussionmentioning

confidence: 99%

CDNA-SNN: A New Spiking Neural Network for Pattern Classification Using Neuronal Assemblies

Saranirad,

Dora,

McGinnity

et al. 2024

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

show abstract

“…Nevertheless, the main limit of spike-based local learning is the diminished performance on complex pattern recognition problems. Different approaches have been explored to bridge this gap, for example using multi-compartment neurons to approximate BP with local mechanisms as in the DPSS [68,69] and BDSP [44] learning rules, developing global gradient-based approaches to train offline the local plasticity mechanisms that will be used online [137][138][139][140], or exploring multimodal association to improve the self-organizing system's performance [20,21,141] since in contrast to labeled data, multiple sensory modalities (e.g. sight, sound, touch) are freely available in the real-world environment.…”

Section: Overcoming Bp Limits For Online Learningmentioning

confidence: 99%

Spike-based local synaptic plasticity: a survey of computational models and neuromorphic circuits

Khacef,

Klein,

Cartiglia

et al. 2023

Neuromorph. Comput. Eng.

View full text Add to dashboard Cite

Understanding how biological neural networks carry out learning using spike-based local plasticity mechanisms can lead to the development of real-time, energy-efficient, and adaptive neuromorphic processing systems. A large number of spike-based learning models have recently been proposed following different approaches. However, it is difficult to assess if these models can be easily implemented in neuromorphic hardware, and to compare their features and ease of implementation. To this end, in this survey, we provide an overview of representative brain-inspired synaptic plasticity models and mixed-signal CMOS neuromorphic circuits within a unified framework. We review historical, experimental, and theoretical approaches to modeling synaptic plasticity, and we identify computational primitives that can support low-latency and low-power hardware implementations of spike-based learning rules. We provide a common definition of a locality principle based on pre- and post-synaptic neural signals, which we propose as an important requirement for physical implementations of synaptic plasticity circuits. Based on this principle, we compare the properties of these models within the same framework, and describe a set of mixed-signal electronic circuits that can be used to implement their computing principles, and to build efficient on-chip and online learning in neuromorphic processing systems.

show abstract

“…A spiking version of the deep ResNet architecture (STS-ResNet) also achieves good performance for gesture recognition as well (Samadzadeh et al, 2020). A recent study develops a bio-plausible method using SNN and STDP that achieves very good results (Safa et al, 2021). The classifier is a Support Vector Machine (SVM) applied to the feature vectors as output from the SNN.…”

Section: Related Workmentioning

confidence: 99%

A robust event-driven approach to always-on object recognition

Grimaldi¹,

Boutin²,

Ieng³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>We propose a neuromimetic architecture that can perform always-on pattern recognition. To achieve this, we have extended an existing event-based algorithm (Lagorce et al., 2017), which introduced novel spatio-temporal features as a Hierarchy Of Time-Surfaces (HOTS). Built from asynchronous events captured by a neuromorphic camera, these time surfaces allow to encode the local dynamics of a visual scene and to create an efficient event-based pattern recognition architecture. Inspired by neuroscience, we have extended this method to improve its performance. First, we add a homeostatic gain control on the activity of neurons to improve the learning of spatio-temporal patterns (Grimaldi et al., 2021). We also provide a new mathematical formalism that allows an analogy to be drawn between the HOTS algorithm and Spiking Neural Networks (SNN). Following this analogy, we transform the offline pattern categorization method into an online and event-driven layer. This classifier uses the spiking output of the network to define new time surfaces and we then perform the online classification with a neuromimetic implementation of a multinomial logistic regression. These improvements not only consistently increase the performance of the network, but also bring this event-driven pattern recognition algorithm fully online. The results have been validated on different datasets: PokerDVS (Serrano-Gotarredona and Linares-Barranco, 2015), N-MNIST (Orchard et al., 2015a) and DVS Gesture (Amir et al., 2017). This demonstrates the efficiency of this bio-realistic SNN for ultra-fast object categorization through an event-by-event decision making process.</p>

show abstract

Event Camera Data Classification Using Spiking Networks with Spike-Timing-Dependent Plasticity

Cited by 9 publications

References 67 publications

CDNA-SNN: A New Spiking Neural Network for Pattern Classification Using Neuronal Assemblies

CDNA-SNN: A New Spiking Neural Network for Pattern Classification Using Neuronal Assemblies

Spike-based local synaptic plasticity: a survey of computational models and neuromorphic circuits

A robust event-driven approach to always-on object recognition

Contact Info

Product

Resources

About