Corpus ID: 236428732

Temporal-wise Attention Spiking Neural Networks for Event Streams Classification

  title={Temporal-wise Attention Spiking Neural Networks for Event Streams Classification},
  author={Man Yao and Huanhuan Gao and Guangshe Zhao and Dingheng Wang and Yihan Lin and Zhaoxu Yang and Guoqi Li},
  • Man Yao, Huanhuan Gao, +4 authors Guoqi Li
  • Published 2021
  • Computer Science
  • ArXiv
How to effectively and efficiently deal with spatiotemporal event streams, where the events are generally sparse and non-uniform and have the μs temporal resolution, is of great value and has various real-life applications. Spiking neural network (SNN), as one of the brain-inspired event-triggered computing models, has the potential to extract effective spatio-temporal features from the event streams. However, when aggregating individual events into frames with a new higher temporal resolution… Expand


Efficient Processing of Spatio-Temporal Data Streams With Spiking Neural Networks
A novel method to obtain highly accurate SNNs for sequence processing by modifying the ANN training before conversion, such that delays induced by ANN rollouts match the propagation delays in the targeted SNN implementation. Expand
Spatio-Temporal Backpropagation for Training High-Performance Spiking Neural Networks
A spatio-temporal backpropagation (STBP) algorithm for training high-performance SNNs is proposed, which combines the layer-by-layer spatial domain (SD) and the timing-dependent temporal domain (TD), and does not require any additional complicated skill. Expand
Comparing SNNs and RNNs on Neuromorphic Vision Datasets: Similarities and Differences
Extensive insights regarding recognition accuracy, feature extraction, temporal resolution and contrast, learning generalization, computational complexity and parameter volume are provided, which are beneficial for the model selection on different workloads and even for the invention of novel neural models in the future. Expand
LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing
A leaky integrate and analog fire (LIAF) neuron model is proposed so that analog values can be transmitted among neurons, and a deep network termed LIAF-Net is built on it for efficient spatiotemporal processing. Expand
Recurrent Spatial-Temporal Attention Network for Action Recognition in Videos.
  • Wenbin Du, Yali Wang, Yu Qiao
  • Medicine
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • 2018
The experimental results show that, the proposed RSTAN outperforms other recent RNN-based approaches on UCF101 and HMDB51 as well as achieves the state-of-the-art on JHMDB. Expand
Efficient Training of Supervised Spiking Neural Network via Accurate Synaptic-Efficiency Adjustment Method
Simulation results indicate that the proposed accurate synaptic-efficiency adjustment method possesses higher learning performance than the existing other methods and achieves the state-of-the-art efficiency in the training of SNN. Expand
LISNN: Improving Spiking Neural Networks with Lateral Interactions for Robust Object Recognition
This work model the lateral interactions between spatially adjacent neurons and integrate it into the spiking neuron membrane potential formula, then build a multi-layer SNN on a popular deep learning framework, i. Expand
SLAYER: Spike Layer Error Reassignment in Time
A new general back Propagation mechanism for learning synaptic weights and axonal delays which overcomes the problem of non-differentiability of the spike function and uses a temporal credit assignment policy for backpropagating error to preceding layers is introduced. Expand
Long-Term Temporal Convolutions for Action Recognition
It is demonstrated that LTC-CNN models with increased temporal extents improve the accuracy of action recognition and the impact of different low-level representations, such as raw values of video pixels and optical flow vector fields, and the importance of high-quality optical flow estimation for learning accurate action models. Expand
CSNN: An Augmented Spiking based Framework with Perceptron-Inception
This work proposes a CNN-SNN (CSNN) model to combine feature learning ability of CNNs with cognition ability of SNNs, and evaluates the CSNN model on the MNIST and its variants, including learning capabilities, encoding mechanisms, robustness to noisy stimuli and its classification performance. Expand