activation-based method
- North America > Canada (0.04)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
- Asia > South Korea > Gyeongsangbuk-do > Pohang (0.04)
- Asia > Middle East > Jordan (0.04)
Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networks
For the gradient computation across the time domain in Spiking Neural Networks (SNNs) training, two different approaches have been independently studied. The first is to compute the gradients with respect to the change in spike activation (activation-based methods), and the second is to compute the gradients with respect to the change in spike timing (timing-based methods). In this work, we present a comparative study of the two methods and propose a new supervised learning method that combines them. The proposed method utilizes each individual spike more effectively by shifting spike timings as in the timing-based methods as well as generating and removing spikes as in the activation-based methods. Experimental results showed that the proposed method achieves higher performance in terms of both accuracy and efficiency than the previous approaches.
Appendix A Versatility of the neuron model In our neuron model, depending on the decay coefficients
The SRM-based back-propagation can be summarized using the relationship between the potentials as follows. Hyper-parameters used for loss landscape estimation (Section 3.4) and random spike-train matching Some of the hyper-parameters were not mentioned in the paper. Table A1: Hyper-parameters used for loss landscape estimation (Section 3.4) and random spike-train matching
- North America > Canada > British Columbia > Metro Vancouver Regional District > Vancouver (0.04)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
- Asia > South Korea > Gyeongsangbuk-do > Pohang (0.04)
- Asia > Middle East > Jordan (0.04)
Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networks
For the gradient computation across the time domain in Spiking Neural Networks (SNNs) training, two different approaches have been independently studied. The first is to compute the gradients with respect to the change in spike activation (activation-based methods), and the second is to compute the gradients with respect to the change in spike timing (timing-based methods). In this work, we present a comparative study of the two methods and propose a new supervised learning method that combines them. The proposed method utilizes each individual spike more effectively by shifting spike timings as in the timing-based methods as well as generating and removing spikes as in the activation-based methods. Experimental results showed that the proposed method achieves higher performance in terms of both accuracy and efficiency than the previous approaches.