Reproduce “General Self-Prediction Enhancement for Spiking Neurons” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Zihan Huang, Zijie Xu, Yihan Huang, Shanshan Jia, Tong Bu, Yiting Dong, Wenxuan Liu, Jianhao Ding and 2 more
The authors introduce a local prediction-current state for spiking neural networks, using each neuron's recent inputs and outputs to influence its next membrane state and add a gradient route. On sequential CIFAR-10, images presented one column per time step for 32 steps, PLIF accuracy is 83.52% with the full method, versus 83.03% detached and 82.54% baseline; gains are not universal.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.