Memristive nanodevices can feature a compact multi-level non-volatile memory function, but are prone to device variability. We propose a novel neural network-based computing paradigm, which exploits their specific physics, and which has virtual immunity to their variability. Memristive devices are used as synapses in a spiking neural network performing unsupervised learning. They learn using a simplified and customized "spike timing dependent plasticity" rule. In the network, neurons' threshold is adjusted following a homeostasis-type rule. We perform system level simulations with an experimentally verifiedmodel of the memristive devices' behavior. They show, on the textbook case of character recognition, that performance can compare with traditional supervised networks of similar complexity. They also show that the system can retain functionality with extreme variations of various memristive devices' parameters (a relative standard dispersion of more than 50% is tolerated on all device parameters), thanks to the robustness of the scheme, its unsupervised nature, and the capability of homeostasis. Additionally the network can adjust to stimuli presented with different coding schemes, is particularly robust to read disturb effects and does not require unrealistic control on the devices' conductance. These results open the way for a novel design approach for ultra-adaptive electronic systems.

Molecule‐based devices are envisioned to complement silicon devices by providing new functions or by implementing existing functions at a simpler process level and lower cost, by virtue of their self‐organization capabilities. Moreover, they are not bound to von Neuman architecture and this feature may open the way to other architectural paradigms. Neuromorphic electronics is one of them. Here, a device made of molecules and nanoparticles—a nanoparticle organic memory field‐effect transistor (NOMFET)—that exhibits the main behavior of a biological spiking synapse is demonstrated. Facilitating and depressing synaptic behaviors can be reproduced by the NOMFET and can be programmed. The synaptic plasticity for real‐time computing is evidenced and described by a simple model. These results open the way to rate‐coding utilization of the NOMFET in dynamical neuromorphic computing circuits.

We demonstrate a unique energy efficient methodology to use Phase Change Memory (PCM) as synapse in ultra-dense large scale neuromorphic systems. PCM devices with different chalcogenide materials were characterized to demonstrate synaptic behavior. Multiphysical simulations were used to interpret the results. We propose special circuit architecture ("the 2-PCM synapse"), read, write, and reset programming schemes suitable for the use of PCM in neural networks. A versatile behavioral model of PCM which can be used for simulating large scale neural systems is introduced. First demonstration of complex visual pattern extraction from real world data using PCM synapses in a 2-layer spiking neural network (SNN) is shown. System power analysis for different scaled PCM technologies is also provided.