Search Results
Multilevel HfO2-based RRAM devices for low-power neuromorphic networks
Training and recognition with neural networks generally require high throughput, high energy efficiency, and scalable circuits to enable artificial intelligence tasks to be operated at the edge, i.e., in battery-powered portable devices and other limited-energy environments. In this scenario, scalable resistive memories have been proposed as artificial synapses thanks to their scalability, reconfigurability, and high-energy efficiency, and thanks to the ability to perform analog computation by physical laws in hardware. In this work, we study the material, device, and architecture aspects of resistive switching memory (RRAM) devices for implementing a 2-layer neural network for pattern recognition. First, various RRAM processes are screened in view of the device window, analog storage, and reliability. Then, synaptic weights are stored with 5-level precision in a 4 kbit array of RRAM devices to classify the Modified National Institute of Standards and Technology (MNIST) dataset. Finally, classification performance of a 2-layer neural network is tested before and after an annealing experiment by using experimental values of conductance stored into the array, and a simulation-based analysis of inference accuracy for arrays of increasing size is presented. Our work supports material-based development of RRAM synapses for novel neural networks with high accuracy and low-power consumption. © 2019 Author(s).
Toward Reliable Multi-Level Operation in RRAM Arrays: Improving Post-Algorithm Stability and Assessing Endurance/Data Retention
Achieving a reliable multi-level operation in resistive random access memory (RRAM) arrays is currently a challenging task due to several threats like the post-algorithm instability occurring after the levels placement, the limited endurance, and the poor data retention capabilities at high temperature. In this paper, we introduced a multi-level variation of the state-of-the-art incremental step pulse with verify algorithm (M-ISPVA) to improve the stability of the low resistive state levels. This algorithm introduces for the first time the proper combination of current compliance control and program/verify paradigms. The validation of the algorithm for forming and set operations has been performed on 4-kbit RRAM arrays. In addition, we assessed the endurance and the high temperature multi-level retention capabilities after the algorithm application proving a 1 k switching cycles stability and a ten years retention target with temperatures below 100 °C.
Neuromorphic on-chip recognition of saliva samples of COPD and healthy controls using memristive devices
Chronic Obstructive Pulmonary Disease (COPD) is a life-threatening lung disease, affecting millions of people worldwide. Implementation of Machine Learning (ML) techniques is crucial for the effective management of COPD in home-care environments. However, shortcomings of cloud-based ML tools in terms of data safety and energy efficiency limit their integration with low-power medical devices. To address this, energy efficient neuromorphic platforms can be used for the hardware-based implementation of ML methods. Therefore, a memristive neuromorphic platform is presented in this paper for the on-chip recognition of saliva samples of COPD patients and healthy controls. Results of its performance evaluations showed that the digital neuromorphic chip is capable of recognizing unseen COPD samples with accuracy and sensitivity values of 89% and 86%, respectively. Integration of this technology into personalized healthcare devices will enable the better management of chronic diseases such as COPD. © 2020, The Author(s).
Enhanced thermal stability of yttrium oxide-based RRAM devices with inhomogeneous Schottky-barrier
This work addresses the thermal stability of bipolar resistive switching in yttrium oxide-based resistive random access memory revealed through the temperature dependence of the DC switching behavior. The operation voltages, current levels, and charge transport mechanisms are investigated at 25 °C, 85 °C, and 125 °C, and show overall good temperature immunity. The set and reset voltages, as well as the device resistance in both the high and low resistive states, are found to scale inversely with increasing temperatures. The Schottky-barrier height was observed to increase from approximately 1.02 eV at 25 °C to approximately 1.35 eV at 125 °C, an uncommon behavior explained by interface phenomena. © 2020 Author(s).
Toward Reliable Compact Modeling of Multilevel 1T-1R RRAM Devices for Neuromorphic Systems
In this work, three different RRAM compact models implemented in Verilog-A are analyzed and evaluated in order to reproduce the multilevel approach based on the switching capability of experimental devices. These models are integrated in 1T-1R cells to control their analog behavior by means of the compliance current imposed by the NMOS select transistor. Four different resistance levels are simulated and assessed with experimental verification to account for their multilevel capability. Further, an Artificial Neural Network study is carried out to evaluate in a real scenario the viability of the multilevel approach under study.
Operando diagnostic detection of interfacial oxygen ‘breathing’ of resistive random access memory by bulk-sensitive hard X-ray photoelectron spectroscopy
The HfO2-based resistive random access memory (RRAM) is one of the most promising candidates for non-volatile memory applications. The detection and examination of the dynamic behavior of oxygen ions/vacancies are crucial to deeply understand the microscopic physical nature of the resistive switching (RS) behavior. By using synchrotron radiation based, non-destructive and bulk-sensitive hard X-ray photoelectron spectroscopy (HAXPES), we demonstrate an operando diagnostic detection of the oxygen ‘breathing’ behavior at the oxide/metal interface, namely, oxygen migration between HfO2 and TiN during different RS periods. The results highlight the significance of oxide/metal interfaces in RRAM, even in filament-type devices. IMPACT STATEMENT: The oxygen ‘breathing’ behavior at the oxide/metal interface of filament-type resistive random access memory devices is operandoly detected using hard X-ray photoelectron spectroscopy as a diagnostic tool. © 2019, © 2019 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
Role of Oxygen Defects in Conductive-Filament Formation in Y2O3-Based Analog RRAM Devices as Revealed by Fluctuation Spectroscopy
Low-frequency noise in Y2O3-based resistive random-access memory devices with analog switching is studied at intermediate resistive states and as a function of dc cycling. A universal 1/fα-type behavior is found, with a frequency exponent of α≈1.2 that is independent of the applied reset voltage or the device resistance and is attributed to the intrinsic abundance of oxygen vacancies unique to the structure of yttria. Remarkably, the noise magnitude in the high resistive state systematically decreases through dc training. This effect is attributed to the stabilization of the conductive filament via the consumption of oxygen vacancies, thus reducing the number of active fluctuators in the vicinity of the filament.