S. Bianchi

Papers

Total Citations

H-Index

About

S. Bianchi’s research lies at the intersection of neuromorphic computing, bio-inspired artificial intelligence, and adaptive learning systems. Their most notable contribution is the development of a bio-inspired recurrent neural network that integrates self-adaptive neurons with phase-change memory (PCM) synapses, specifically designed to solve reinforcement learning tasks. This work, published in 2020 with 12 citations, addresses a fundamental challenge in AI: creating systems that learn autonomously from experience and dynamically adapt to changing environments, mirroring the plasticity of biological neural networks. By leveraging PCM synapses, Bianchi’s approach enables efficient, hardware-friendly implementations of adaptive learning, bridging the gap between neuroscience and machine learning. Their research emphasizes the importance of synaptic morphology modification—a key mechanism in neurobiological systems—to achieve continuous learning without external supervision. While still early in their career, Bianchi’s work has already garnered attention for its potential to advance energy-efficient, autonomous AI systems. Their contributions are particularly relevant for students and researchers exploring neuromorphic hardware, reinforcement learning, and self-adaptive algorithms, offering a glimpse into the future of lifelong learning machines.