👍 New paper is now available online in Neural Networks!

My mentee, Suhee Cho, and I recently published a paper presenting a metaplasticity model inspired by human working memory.
In this study, based on my previous work (Lee et al., 2020), we implemented distinct types of synapses from stable to flexible, and randomly intermixing them to train synaptic connections with varying degrees of flexibility. We found that our model achieved a balanced tradeoff between memory capacity and performance without requiring additional training or structural modifications, dynamically allocating memory resources to retain both old and new information.

I am deeply grateful for the invaluable guidance and supervision of Prof. Se-Bum Paik.