Alexey Serenko
Papers
1
Total Citations
4
H-Index
1
About
Alexey Serenko is a computational neuroscientist whose research lies at the intersection of spiking neural networks, unsupervised learning, and neuromorphic computing. His most-cited work, "A Non-fully-Connected Spiking Neural Network with STDP for Solving a Classification Task" (2020, 4 citations), introduces a biologically plausible architecture that leverages spike-timing-dependent plasticity (STDP) to perform pattern classification without full connectivity. This contribution challenges conventional fully connected models by demonstrating that sparse, local connectivity can achieve competitive accuracy while significantly reducing computational overhead—a key step toward energy-efficient, brain-inspired hardware. Serenko’s approach highlights the potential of STDP as a core learning rule for neuromorphic systems, offering a scalable framework for real-time sensory processing. Though his citation count is modest, his work is foundational for researchers exploring low-power, event-driven neural networks. By bridging theoretical neuroscience with practical engineering constraints, Serenko advances the development of autonomous agents capable of learning from sparse, temporal data. His research is particularly relevant for students and engineers seeking to design efficient, biologically grounded AI systems that operate under resource limitations.
Research Focus
Key Achievements
Top Papers
- 1