Yoshimasa Kubo

This study uses recurrent neural networks to show that REM-like sleep reduces memory interference by decorrelating task-specific neuronal populations and reactivating memory traces through synaptic pruning.

This paper introduces Neuromodulated Equilibrium Learning (NEL), a single-equilibrium reward-based framework, and evaluates its performance on image datasets compared to multi-phase baselines.

This paper introduces a reward-based variant of equilibrium propagation that uses sparse reward signals instead of full target vectors, achieving performance close to conventional EP on multiple datasets.

This paper introduces the Dendritic Wave Recurrent Neural Network (DW-RNN), which improves upon wave recurrent neural networks by adding dendritic input integration, achieving better performance and stability on sequential tasks.

This paper proposes an EP-based SNN framework with predictive learning in LIF neurons, showing competitive accuracy on image classification tasks while using a biologically motivated learning rule.

This paper combines equilibrium propagation with backpropagation in an actor-critic reinforcement learning framework, showing improved consistency in high-reward behavior on control tasks.

This paper proposes a predictive learning rule for neurons based on minimizing metabolic cost and maximizing blood supply impact, validated through simulations and animal data.