Extraction of temporally correlated features from dynamic vision sensors with spike-timing-dependent plasticity

Bichler, Olivier; Querlioz, Damien; Thorpe, Simon J.; Bourgoin, Jean‐Philippe; Gamrat, Christian

doi:10.1016/j.neunet.2012.02.022

Cited by 137 publications

(134 citation statements)

References 19 publications

Supporting

Mentioning

132

Contrasting

Unclassified

Order By: Relevance

“…12.7f1, f2 illustrate the case where forward and backward spikes have opposite polarities, resulting in a symmetric STDP update function ξ (Δ T ). negative STDP update whenever there is a post-synaptic spike sufficiently apart from a pre-synaptic one; and produces LTP (long-term potentiation) if pre-and post-synaptic spikes happen within a given time window [70,94]. Figure 12.7h1, h2 illustrate a similar STDP update behavior, except that update (whether positive or negative) is restricted to a constraint time window.…”

Section: Combining Memristors and Cmos Neurons For Stdpmentioning

confidence: 92%

“…For example, Fig. 12.1 illustrates the basic principle of ED sensing and signal encoding, by showing the characteristics of one of the most popular ED vision sensors, the "Dynamic Vision Sensor" (DVS) [42][43][44][45] developed first during project CAVIAR [53] and used in a variety of applications [29,[54][55][56][57][58][59][60][61][62][63][64][65][66][67][68][69][70]. Whenever a pixel senses a change of light above a threshold it sends out of the chip an "event" in the form of a digital word (x, y, p) representing its address (x, y) and a polarity bit p (positive for a dark to bright change and negative for a bright to dark change) that typically needs fractions of a micro-second to be communicated.…”

Section: Spiking Neural Network For Event-driven Sensing and Processingmentioning

confidence: 99%

See 1 more Smart Citation

Spike-Timing-Dependent-Plasticity in Hybrid Memristive-CMOS Spiking Neuromorphic Systems

Serrano-Gotarredona

Linares-Barranco

2013

Memristors and Memristive Systems

View full text Add to dashboard Cite

Section: Combining Memristors and Cmos Neurons For Stdpmentioning

confidence: 92%

Section: Spiking Neural Network For Event-driven Sensing and Processingmentioning

confidence: 99%

Spike-Timing-Dependent-Plasticity in Hybrid Memristive-CMOS Spiking Neuromorphic Systems

Serrano-Gotarredona

Linares-Barranco

2013

Memristors and Memristive Systems

View full text Add to dashboard Cite

“…It is available as opensource software at sourcesup.renater.fr/wiki/n2s3 so that its users can share their models and experimental settings to enable others to reproduce their results. In this spirit, N2S3 is distributed with the implementation of two "classical" experiments: handwritten digit recognition on the MNIST dataset [41], [42] and the highway vehicle counting experiment [43].…”

Section: Requirements For a Spiking Neuromorphic Hardware Simulatormentioning

confidence: 99%

Parameter Exploration to Improve Performance of Memristor-Based Neuromorphic Architectures

Shahsavari

Boulet

2018

IEEE Trans. Multi-Scale Comp. Syst.

View full text Add to dashboard Cite

Abstract-The brain-inspired spiking neural network neuromorphic architecture offers a promising solution for a wide set of cognitive computation tasks at a very low power consumption. Due to the practical feasibility of hardware implementation, we present a memristor-based model of hardware spiking neural networks which we simulate with N2S3 (Neural Network Scalable Spiking Simulator), our open source neuromorphic architecture simulator. Although Spiking neural networks are widely used in the community of computational neuroscience and neuromorphic computation, there is still a need for research on the methods to choose the optimum parameters for better recognition efficiency. With the help of our simulator, we analyze and evaluate the impact of different parameters such as number of neurons, STDP window, neuron threshold, distribution of input spikes and memristor model parameters on the MNIST hand-written digit recognition problem. We show that a careful choice of a few parameters (number of neurons, kind of synapse, STDP window and neuron threshold) can significantly improve the recognition rate on this benchmark (around 15 points of improvement for the number of neurons, a few points for the others) with a variability of 4 to 5 points of recognition rate due to the random initialization of the synaptic weights.

show abstract

“…In some recent work with Olivier Bichler and other colleague at the CEA in Saclay we have been looking at how an STDP-based learning mechanism would react to real spiking events provided by one of Tobi Delbruck's Dynamic Vision Sensor chips [1].…”

Section: Stdp Learning With a Dynamic Vision Sensormentioning

confidence: 99%

Spike-Based Image Processing: Can We Reproduce Biological Vision in Hardware?

Thorpe

2012

Computer Vision – ECCV 2012. Workshops and Demonstrations

Self Cite

View full text Add to dashboard Cite

Abstract. Over the past 15 years, we have developed software image processing systems that attempt to reproduce the sorts of spike-based processing strategies used in biological vision. The basic idea is that sophisticated visual processing can be achieved with a single wave of spikes by using the relative timing of spikes in different neurons as an efficient code. While software simulations are certainly an option, it is now becoming clear that it may well be possible to reproduce the same sorts of ideas in specific hardware. Firstly, several groups have now developed spiking retina chips in which the pixel elements send the equivalent of spikes in response to particular events such as increases or a decreases in local luminance. Importantly, such chips are fully asynchronous, allowing image processing to break free of the standard frame based approach. We have recently shown how simple neural network architectures can use the output of such dynamic spiking retinas to perform sophisticated tasks by using a biologically inspired learning rule based on SpikeTime Dependent Plasticity (STDP). Such systems can learn to detect meaningful patterns that repeat in a purely unsupervised way. For example, after just a few minutes of training, a network composed of a first layer of 60 neurons and a second layer of 10 neurons was able to form neurons that could effectively count the number of cars going by on the different lanes of a freeway. For the moment, this work has just used simulations. However, there is a real possibility that the same processing strategies could be implemented in memristor-based hardware devices. If so, it will become possible to build intelligent image processing systems capable of learning to recognize significant events without the need for conventional computational hardware.

show abstract

Extraction of temporally correlated features from dynamic vision sensors with spike-timing-dependent plasticity

Cited by 137 publications

References 19 publications

Spike-Timing-Dependent-Plasticity in Hybrid Memristive-CMOS Spiking Neuromorphic Systems

Spike-Timing-Dependent-Plasticity in Hybrid Memristive-CMOS Spiking Neuromorphic Systems

Parameter Exploration to Improve Performance of Memristor-Based Neuromorphic Architectures

Spike-Based Image Processing: Can We Reproduce Biological Vision in Hardware?

Contact Info

Product

Resources

About