Daniele Ielmini

About

Daniele Ielmini is a leading figure in the field of emerging memory technologies and neuromorphic computing. His research focuses on resistive-switching memory (RRAM), phase-change memory (PCM), and novel threshold switches, which he applies to create brain-inspired hardware that overcomes the limitations of traditional von Neumann architectures. A major contribution is his work on hybrid CMOS/RRAM neural networks, where he demonstrated spike time/rate-dependent plasticity for unsupervised learning, a paper with 71 citations. He has also pioneered the use of highly nonlinear threshold switches to enhance matrix addressing in flexible sensory arrays for wearable and soft robotics applications (87 citations). More recently, Ielmini has advanced bio-inspired recurrent neural networks with self-adaptive neurons and PCM synapses for reinforcement learning, as well as fully integrated analogue closed-loop in-memory computing accelerators based on SRAM. His work bridges materials science, circuit design, and artificial intelligence, pushing the boundaries of energy-efficient, adaptive computing systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Enhancing the Matrix Addressing of Flexible Sensory Arrays by a Highly Nonlinear Threshold Switch

   87 citations · 2018
2. 2
   Demonstration of hybrid CMOS/RRAM neural networks with spike time/rate-dependent plasticity

   71 citations · 2016
3. 3
   A Bio-Inspired Recurrent Neural Network with Self-Adaptive Neurons and PCM Synapses for Solving Reinforcement Learning Tasks

   12 citations · 2020
4. 4
   A fully integrated analogue closed-loop in-memory computing accelerator based on static random-access memory

   2 citations · 2026

Key Collaborators

Contact & Links