Mikhail Kiselev

Papers

Total Citations

H-Index

About

Mikhail Kiselev is a rising researcher at the forefront of computational neuroscience and artificial intelligence, with a primary focus on developing biologically plausible learning algorithms. His most notable contribution is the groundbreaking paper "A purely spiking approach to reinforcement learning" (2024), which has already garnered 7 citations. This work introduces a novel framework that leverages spiking neural networks—models that more closely mimic biological neurons—to solve reinforcement learning tasks without relying on traditional rate-based or gradient-based methods. By demonstrating that spiking neurons can directly implement reward-based learning, Kiselev challenges conventional approaches and opens new pathways for energy-efficient, brain-inspired AI systems. His research sits at the intersection of neuromorphic computing, synaptic plasticity, and decision-making, offering insights into how the brain might solve complex learning problems. Though early in his career, Kiselev’s work is already influencing discussions on the future of low-power, event-driven AI architectures. His achievements highlight a commitment to bridging the gap between neural computation and artificial intelligence, making him a promising voice in the quest for more efficient and interpretable learning systems.