Kensuke Yoshida

This paper proposes a theoretical model of schema learning through low-dimensional neural representations formed during sleep-driven dimensionality reduction.

This paper develops a biologically plausible nonlinear dimensionality reduction algorithm inspired by Drosophila olfactory circuits and demonstrates its effectiveness on datasets like entangled rings and MNIST.

The paper reviews computational models showing that intrinsic synaptic dynamics can support stable network performance and may enhance information processing.