Andrea Castagnetti
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Andrea Castagnetti has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
Alain Pegatoquet
Université Côte d'Azur, CNRS, LEAT, Sophia Antipolis, France
2 shared publicationsBenoît Miramond
Université Côte d'Azur, CNRS, LEAT, Sophia Antipolis, France
2 shared publications- Benoît Miramond
LEAT, Université Cǒte d’Azur, CNRS
1 shared publication - Edgar Lemaire
Université Côte d’Azur, CNRS, LEAT
1 shared publication - Frédéric Chorin
Laboratoire Motricité Humaine Éducation Sport Santé (LAMHESS), Université Côte d’Azur, 06100 Nice, France
1 shared publication - Jonathan Courtois
LEAT Univ. Côte d'azur CNRS France
1 shared publication
Latest Publications
- Open Access
- 11 August 2023
- Published by Frontiers Media SA in Frontiers in Neuroscience
- Vol. 17, 1224457
SPIDEN: deep Spiking Neural Networks for efficient image denoising
In recent years, Deep Convolutional Neural Networks (DCNNs) have outreached the performance of classical algorithms for image restoration tasks. However, most of these methods are not suited for computational efficiency. In this work, we investigate Spiking Neural Networks (SNNs) for the specific and uncovered case of image denoising, with the goal of reaching the performance of conventional DCNN while reducing the computational cost. This task is challenging for two reasons. First, as denoising is a regression task, the network has to predict a continuous value (i.e., the noise amplitude) for each pixel of the image, with high precision. Moreover, state of the art results have been obtained with deep networks that are notably difficult to train in the spiking domain. To overcome these issues, we propose a formal analysis of the information conversion processing carried out by the Integrate and Fire (IF) spiking neurons and we formalize the trade-off between conversion error and activation sparsity in SNNs. We then propose, for the first time, an image denoising solution based on SNNs. The SNN networks are trained directly in the spike domain using surrogate gradient learning and backpropagation through time. Experimental results show that the proposed SNN provides a level of performance close to the state of the art with CNN based solutions. Specifically, our SNN achieves 30.18 dB of signal-to-noise ratio on the Set12 dataset, which is only 0.25 dB below the performance of the equivalent DCNN. Moreover we show that this performance can be achieved with low latency, i.e., using few timesteps, and with a significant level of sparsity. Finally, we analyze the energy consumption for different network latencies and network sizes. We show that the energy consumption of SNNs increases with longer latencies, making them more energy efficient compared to CNNs only for very small inference latencies. However, we also show that by increasing the network size, SNNs can provide competitive denoising performance while reducing the energy consumption by 20%.
- 11 August 2023
- Published by Frontiers Media SA in Frontiers in Neuroscience
- Vol. 17, 1224457
Open AccessSPIDEN: deep Spiking Neural Networks for efficient image denoising
In recent years, Deep Convolutional Neural Networks (DCNNs) have outreached the performance of classical algorithms for image restoration tasks. However, most of these methods are not suited for computational efficiency. In this work, we investigate Spiking Neural Networks (SNNs) for the specific and uncovered case of image denoising, with the goal of reaching the performance of conventional DCNN while reducing the computational cost. This task is challenging for two reasons. First, as denoising is a regression task, the network has to predict a continuous value (i.e., the noise amplitude) for each pixel of the image, with high precision. Moreover, state of the art results have been obtained with deep networks that are notably difficult to train in the spiking domain. To overcome these issues, we propose a formal analysis of the information conversion processing carried out by the Integrate and Fire (IF) spiking neurons and we formalize the trade-off between conversion error and activation sparsity in SNNs. We then propose, for the first time, an image denoising solution based on SNNs. The SNN networks are trained directly in the spike domain using surrogate gradient learning and backpropagation through time. Experimental results show that the proposed SNN provides a level of performance close to the state of the art with CNN based solutions. Specifically, our SNN achieves 30.18 dB of signal-to-noise ratio on the Set12 dataset, which is only 0.25 dB below the performance of the equivalent DCNN. Moreover we show that this performance can be achieved with low latency, i.e., using few timesteps, and with a significant level of sparsity. Finally, we analyze the energy consumption for different network latencies and network sizes. We show that the energy consumption of SNNs increases with longer latencies, making them more energy efficient compared to CNNs only for very small inference latencies. However, we also show that by increasing the network size, SNNs can provide competitive denoising performance while reducing the energy consumption by 20%.
- 13 April 2023
- Published by Springer Nature
- p. 574-587
An Analytical Estimation of Spiking Neural Networks Energy Efficiency
- 13 April 2023
- Published by Springer Nature
- p. 574-587
An Analytical Estimation of Spiking Neural Networks Energy Efficiency
- Open Access
- 3 March 2023
- Published by Frontiers Media SA in Frontiers in Neuroscience
- Vol. 17, 1154241
Trainable quantization for Speedy Spiking Neural Networks
Spiking neural networks are considered as the third generation of Artificial Neural Networks. SNNs perform computation using neurons and synapses that communicate using binary and asynchronous signals known as spikes. They have attracted significant research interest over the last years since their computing paradigm allows theoretically sparse and low-power operations. This hypothetical gain, used from the beginning of the neuromorphic research, was however limited by three main factors: the absence of an efficient learning rule competing with the one of classical deep learning, the lack of mature learning framework, and an important data processing latency finally generating energy overhead. While the first two limitations have recently been addressed in the literature, the major problem of latency is not solved yet. Indeed, information is not exchanged instantaneously between spiking neurons but gradually builds up over time as spikes are generated and propagated through the network. This paper focuses on quantization error, one of the main consequence of the SNN discrete representation of information. We argue that the quantization error is the main source of accuracy drop between ANN and SNN. In this article we propose an in-depth characterization of SNN quantization noise. We then propose a end-to-end direct learning approach based on a new trainable spiking neural model. This model allows adapting the threshold of neurons during training and implements efficient quantization strategies. This novel approach better explains the global behavior of SNNs and minimizes the quantization noise during training. The resulting SNN can be trained over a limited amount of timesteps, reducing latency, while beating state of the art accuracy and preserving high sparsity on the main datasets considered in the neuromorphic community.
- 3 March 2023
- Published by Frontiers Media SA in Frontiers in Neuroscience
- Vol. 17, 1154241
Open AccessTrainable quantization for Speedy Spiking Neural Networks
Spiking neural networks are considered as the third generation of Artificial Neural Networks. SNNs perform computation using neurons and synapses that communicate using binary and asynchronous signals known as spikes. They have attracted significant research interest over the last years since their computing paradigm allows theoretically sparse and low-power operations. This hypothetical gain, used from the beginning of the neuromorphic research, was however limited by three main factors: the absence of an efficient learning rule competing with the one of classical deep learning, the lack of mature learning framework, and an important data processing latency finally generating energy overhead. While the first two limitations have recently been addressed in the literature, the major problem of latency is not solved yet. Indeed, information is not exchanged instantaneously between spiking neurons but gradually builds up over time as spikes are generated and propagated through the network. This paper focuses on quantization error, one of the main consequence of the SNN discrete representation of information. We argue that the quantization error is the main source of accuracy drop between ANN and SNN. In this article we propose an in-depth characterization of SNN quantization noise. We then propose a end-to-end direct learning approach based on a new trainable spiking neural model. This model allows adapting the threshold of neurons during training and implements efficient quantization strategies. This novel approach better explains the global behavior of SNNs and minimizes the quantization noise during training. The resulting SNN can be trained over a limited amount of timesteps, reducing latency, while beating state of the art accuracy and preserving high sparsity on the main datasets considered in the neuromorphic community.
- Open Access
Smart Eyeglasses: A Valid and Reliable Device to Assess Spatiotemporal Parameters during Gait
The study aims to determine the validity and reproducibility of step duration and step length parameters measured during walking in healthy participants using an accelerometer embedded in smart eyeglasses. Twenty young volunteers participated in two identical sessions comprising a 30 s gait assessment performed at three different treadmill speeds under two conditions (i.e., with and without a cervical collar). Spatiotemporal parameters (i.e., step duration and step length normalized by the lower limb length) were obtained with both the accelerometer embedded in smart eyeglasses and an optoelectronic system. The relative intra- and inter-session reliability of step duration and step length computed from the vertical acceleration data were excellent for all experimental conditions. An excellent absolute reliability was observed for the eyeglasses for all conditions and concurrent validity between systems was observed. An accelerometer incorporated in smart eyeglasses is accurate to measure step duration and step length during gait.
Open AccessSmart Eyeglasses: A Valid and Reliable Device to Assess Spatiotemporal Parameters during Gait
The study aims to determine the validity and reproducibility of step duration and step length parameters measured during walking in healthy participants using an accelerometer embedded in smart eyeglasses. Twenty young volunteers participated in two identical sessions comprising a 30 s gait assessment performed at three different treadmill speeds under two conditions (i.e., with and without a cervical collar). Spatiotemporal parameters (i.e., step duration and step length normalized by the lower limb length) were obtained with both the accelerometer embedded in smart eyeglasses and an optoelectronic system. The relative intra- and inter-session reliability of step duration and step length computed from the vertical acceleration data were excellent for all experimental conditions. An excellent absolute reliability was observed for the eyeglasses for all conditions and concurrent validity between systems was observed. An accelerometer incorporated in smart eyeglasses is accurate to measure step duration and step length during gait.