New Supervised Hebbian Learning Algorithm for Spiking Neural Networks Outperforms STDP

Researchers have developed a new gradient-free supervised learning algorithm for spiking neural networks (SNNs) called Supervised Spike Agreement-Dependent Plasticity (Supervised SADP). This method directly embeds class information into the Hebbian plasticity computation, unlike previous approaches that used reward modulation. Supervised SADP demonstrated superior performance compared to reward-modulated Spike-Timing-Dependent Plasticity (STDP) on benchmark datasets, achieving significantly higher accuracy on MNIST and Fashion-MNIST while also training faster. AI

IMPACT This new algorithm offers a more efficient and stable gradient-free alternative for supervised learning in spiking neural networks, potentially advancing neuromorphic computing.

RANK_REASON The cluster contains a research paper detailing a novel algorithm for spiking neural networks. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Cohen's kappa
• Fashion-MNIST
• MNIST
• Saptarshi Bej
• Spiking neural networks
• Supervised SADP

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →