Spiking Neural Networks for Frame-based and Event-based Single Object Localization

06/13/2022
by   Sami Barchid, et al.
6

Spiking neural networks have shown much promise as an energy-efficient alternative to artificial neural networks. However, understanding the impacts of sensor noises and input encodings on the network activity and performance remains difficult with common neuromorphic vision baselines like classification. Therefore, we propose a spiking neural network approach for single object localization trained using surrogate gradient descent, for frame- and event-based sensors. We compare our method with similar artificial neural networks and show that our model has competitive/better performance in accuracy, robustness against various corruptions, and has lower energy consumption. Moreover, we study the impact of neural coding schemes for static images in accuracy, robustness, and energy efficiency. Our observations differ importantly from previous studies on bio-plausible learning rules, which helps in the design of surrogate gradient trained architectures, and offers insight to design priorities in future neuromorphic technologies in terms of noise characteristics and data encoding methods.

READ FULL TEXT

page 16

page 17

page 19

page 21

research
05/12/2021

Deep Spiking Convolutional Neural Network for Single Object Localization Based On Deep Continuous Local Learning

With the advent of neuromorphic hardware, spiking neural networks can be...
research
05/18/2021

Sparse Spiking Gradient Descent

There is an increasing interest in emulating Spiking Neural Networks (SN...
research
04/25/2023

Uncovering the Representation of Spiking Neural Networks Trained with Surrogate Gradient

Spiking Neural Networks (SNNs) are recognized as the candidate for the n...
research
07/07/2020

Multi-Tones' Phase Coding (MTPC) of Interaural Time Difference by Spiking Neural Network

Inspired by the mammal's auditory localization pathway, in this paper we...
research
04/13/2023

Temporal Knowledge Sharing enable Spiking Neural Network Learning from Past and Future

Spiking neural networks have attracted extensive attention from research...
research
05/28/2023

Evolving Connectivity for Recurrent Spiking Neural Networks

Recurrent spiking neural networks (RSNNs) hold great potential for advan...
research
04/20/2023

Efficient Uncertainty Estimation in Spiking Neural Networks via MC-dropout

Spiking neural networks (SNNs) have gained attention as models of sparse...

Please sign up or login with your details

Forgot password? Click here to reset