No abstract

No abstract

A fully-unsupervised learning algorithm for reaching self-organization in neuromorphic architectures is provided in this work. We experimentally demonstrate spike-timing dependent plasticity (STDP) in Oxide-based Resistive Random Access Memory (OxRAM) devices, and propose a set of waveforms in order to induce symmetric conductivity changes. An empirical model is used to describe the observed plasticity. A neuromorphic system based on the tested devices is simulated, where the developed learning algorithm is tested, involving STDP as the local learning rule. The design of the system and learning scheme permits to concatenate multiple neuromorphic layers, where autonomous hierarchical computing can be performed.

In this work, TiN/Ti/HfO2/W memristors have been investigated to mimic the spike-time dependent plasticity (STDP) of biological synapses at multiple time scales. For this purpose, a smart software tool has been implemented to control the instrumentation and to perform a dedicated ultra-fast pulsed characterization. Different time scales, from tens of milliseconds to hundreds of nanoseconds, have been explored to emulate the STDP learning rule in electronic synapses. The impact of such times on the synaptic weight potentiation and depression characteristics has also been discussed.

In this work, the impact of different HfO2/Al2O3-based multilayer dielectric stack (DS) configurations on the electrical characteristics and on the resistive switching (RS) performance of Ni/Insulator/Silicon devices has been systematically investigated. Significant differences are observed in the electrical characteristics of the fabricated bilayer, trilayer and pentalayer stacks compared to a single HfO2 layer of the same physical thickness. The RS analysis has shown similar low resistance state currents and set voltages for all the DS combinations whereas currents at the high resistance state and reset voltages depend on the DS. The shift of the reset voltage to lower values for HfO2 and Al2O3/HfO2/Al2O3 cases is explained by the results from thermal simulations that reveal that these differences could be associated to the different temperature distributions at the narrowest part of the conductive filament immediately before the thermally triggered reset process occurs.