RSNN: Recurrent Spiking Neural Networks for Dynamic Spatial-Temporal Information Processing
Open Access
- 28 October 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 10602-10610
Abstract
Spiking Neural Networks (SNNs) have great advantages in discrete event data processing because of their binary digital computation form. However, due to the limitation of the current structures of SNNs, the original event data needs to be preprocessed to reduce the time calculation steps and information redundancy. The traditional methods of dividing data into frames lead to the loss of a large amount of time information. In this paper, we proposed an efficient Recurrent Spiking Neural Network (RSNN) to reduce the time domain information loss of original slice samples with the spiking based neural dynamics for processing the dynamic spatial-temporal information. By constructing the Recurrent Spiking Neural Network model, the recurrent structure was used to preprocess slices before it was further input into the spiking structure to enhance the time correlation between slices. In addition, in order to match the two-dimensional spatial structure of data sample frames efficiently, this paper adapts a variation of structures of the recurrent neural network, named Convolution LSTM (CONLSTM). Through experiments on event based datasets such as DVS128-Gesture and CIFAR10-DVS, we find that the proposed model could not only behave better than some other spiking based models but also save energy and power consumption which paves the way for practical applications of neuromorphic hardware.Keywords
This publication has 19 references indexed in Scilit:
- Real Spike: Learning Real-Valued Spikes for Spiking Neural Networks2022
- RecDis-SNN: Rectifying Membrane Potential Distribution for Directly Training Spiking Neural Networks2022
- Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks2021
- Deep learning incorporating biologically inspired neural dynamics and in-memory computingNature Machine Intelligence, 2020
- Multi-threaded learning control mechanism for neural networksFuture Generation Computer Systems, 2018
- Recent advances in convolutional neural networksPattern Recognition, 2018
- STDP-based spiking deep convolutional neural networks for object recognitionNeural Networks, 2018
- A Low Power, Fully Event-Based Gesture Recognition System2017
- Darwin: A neuromorphic hardware co-processor based on spiking neural networksJournal of Systems Architecture, 2017
- Event-based 3D SLAM with a depth-augmented dynamic vision sensor2014