Giacomo Pedretti
Papers
3
Total Citations
85
H-Index
2
About
Giacomo Pedretti is a leading researcher in neuromorphic computing and in-memory computing, whose work bridges the gap between artificial intelligence and brain-inspired hardware. His key research areas include resistive-switching memory (RRAM) and phase-change memory (PCM) for neural networks, as well as analogue closed-loop computing architectures. Pedretti’s major contributions include the first demonstration of hybrid CMOS/RRAM neural networks with spike time/rate-dependent plasticity, enabling unsupervised learning that mimics the human brain’s ability to recognize patterns without pre-determined training sets. This groundbreaking work, with 71 citations, directly challenges the limitations of von Neumann architectures. He further advanced the field by developing a bio-inspired recurrent neural network using PCM synapses and self-adaptive neurons for reinforcement learning, allowing systems to learn from experience in dynamic environments. Most recently, Pedretti introduced a fully integrated analogue in-memory computing accelerator based on static random-access memory, achieving closed-loop operation with minimal energy consumption. His work has profound implications for edge computing, autonomous systems, and energy-efficient AI, positioning him as a key innovator in next-generation computing hardware.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3