MSTDP: A More Biologically Plausible Learning
This work addresses the challenge of creating more biologically plausible learning models for neuroscience and AI researchers, though it appears incremental as it builds on existing STDP concepts.
The authors tackled the problem of bridging biological and artificial learning by proposing MSTDP, a framework that uses only spike-timing dependent plasticity (STDP) rules for supervised and unsupervised learning without global loss or supervision. They verified it on MNIST for classification and generation tasks, achieving results that demonstrate its functionality.
Spike-timing dependent plasticity (STDP) which observed in the brain has proven to be important in biological learning. On the other hand, artificial neural networks use a different way to learn, such as Back-Propagation or Contrastive Hebbian Learning. In this work, we propose a new framework called mstdp that learn almost the same way biological learning use, it only uses STDP rules for supervised and unsupervised learning and don' t need a global loss or other supervise information. The framework works like an auto-encoder by making each input neuron also an output neuron. It can make predictions or generate patterns in one model without additional configuration. We also brought a new iterative inference method using momentum to make the framework more efficient, which can be used in training and testing phases. Finally, we verified our framework on MNIST dataset for classification and generation task.