- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes NLT-prop, an online learning method for spiking neural networks. The method divides the temporal Jacobian into local and nonlocal components and uses low-rank approximations to preserve nonlocal temporal information with linear eligibility-trace memory. Experiments on five datasets show competitive performance compared with BPTT and existing online learning methods.
Critical strengths
The paper proposes a structured low-rank approximation to preserve nonlocal temporal information with linear eligibility-trace memory. This provides a useful way to improve temporal credit assignment in online SNN learning while reducing memory requirements. The experimental results also show competitive performance.
Critical weaknesses
The proposed approximations and computational efficiency are not sufficiently validated. The method uses rank-one approximations and shares factors across different nonlocal orders, but the effects of these designs are not fully studied. In addition, the paper lacks direct comparisons of training time and computational cost with existing methods. These issues make it difficult to evaluate the effectiveness and practical benefits of the proposed method.
Questions for authors
- Why is rank-one approximation used? Can the authors compare different approximation ranks to show their effects on accuracy and memory usage?
- What is the effect of sharing the presynaptic factor across different nonlocal orders? Can the authors compare shared and independent factors?
- Can the authors provide training time and computational cost comparisons with existing online learning methods to demonstrate the practical efficiency of NLT-prop?
Thank you for your constructive feedback. Your questions have helped us improve the rigor of both the work and its presentation. We have uploaded a revised PDF with the changes highlighted in blue. We address your questions below.
Comment/Question:
Answer: We chose rank one to balance approximation error and computational efficiency. We have added an experiment comparing the accuracy and computational efficiency of NLT-prop with nonlocal trace ranks of 1, 2, and 3, together with a derivation of the updates for higher ranks (Appendix B.8, Table 9).
Higher ranks reduce accuracy on SHD and improve it by less than one percentage point on DVS Gesture. These limited accuracy benefits come with a substantial increase in training cost. On DVS Gesture, ranks 2 and 3 increase training time to 32.85 and 43.13 times that of rank one, respectively, and increase peak GPU memory usage by 16.7% and 41.0%. On SHD, training time increases to 4.55 and 4.37 times that of rank one. These results favor rank one as a practical choice.
Rank-one factorizations have also been used for local traces in existing online learning methods. We extend this approach to nonlocal contributions and use a different procedure to obtain the presynaptic and postsynaptic traces.
Comment/Question:
Answer: Using the current presynaptic factor pt for both local and nonlocal contributions, in place of pt−1 for the nonlocal contributions, is an approximation. Its purpose is to reduce the additional computational cost of retaining nonlocal terms while preserving accuracy.
The intuition comes from the common presynaptic origin of different propagation paths. Consider a source contribution B introduced at time t−3. In the absence of further source terms, all local and nonlocal paths originating from B retain the same presynaptic activity and can therefore share a presynaptic factor (Eq. 32). If subsequent inputs have the same presynaptic direction, that shared direction can still represent the presynaptic dependence exactly. When subsequent inputs have different directions, factor sharing introduces an approximation error whose bound is given in Appendix A.6.
The added explanation in Appendix A.6 shows how this approximation reduces computation and storage. We also added an experiment comparing the shared factor with retaining a separate factor for the nonlocal contributions (Appendix B.9, Table 10). Sharing reduces training time, SynOps, and the spike rate, and improves accuracy by 2.64 percentage points. Two possible explanations for the accuracy gain are interactions with other approximation errors and a regularization effect from constraining each sample's gradient contribution to a common presynaptic direction.
Comment/Question:
Answer: Yes. We have added computational efficiency measurements for the different methods in Appendix B.7, Table 7. NLT-prop has training times close to those of the two main competing methods, OTTT and pp-prop, on SHD and DMTS, and is faster than both on DVS Gesture. It also offers advantages in peak GPU memory usage, spike rate, and SynOps.
The reductions in spike rate and SynOps are particularly useful for systems that exploit sparse activity. Their potential energy benefits are only partly reflected in our measurements on the A800. Neuromorphic hardware and implementations that exploit sparsity could make fuller use of these reductions to save energy and memory. Together with the accuracy improvements and the stronger learning and generalization of long-term dependencies shown in Section 4.7 and Figure 2, these benefits make the modest additional training time worthwhile.