Refine
Year of publication
Document Type
Way of publication
- Open Access (10)
Language
- English (74)
Keywords
- RRAM (43)
- neural network (13)
- HfO2 (12)
- Multilevel switching (11)
- Graphene (9)
- memristive device (9)
- memristive switching (4)
- resistive switching (4)
- Neural network (3)
- Transistor (3)
Institute
BTU
The crossbar structure of Resistive-switching random access memory (RRAM) arrays enabled the In-Memory Computing circuits paradigm, since they imply the native acceleration of a crucial operations in this scenario, namely the Matrix-Vector-Multiplication (MVM). However, RRAM arrays are affected by several issues materializing in conductance variations that might cause severe performance degradation. A critical
one is related to the drift of the low conductance states appearing
immediately at the end of program and verify algorithms that
are mandatory for an accurate multi-level conductance operation. In this work, we analyze the benefits of a new programming
algorithm that embodies Set and Reset switching operations to
achieve better conductance control and lower variability. Data
retention analysis performed with different temperatures for 168
hours evidence its superior performance with respect to standard programming approach. Finally, we explored the benefits
of using our methodology at a higher abstraction level, through
the simulation of an Artificial Neural Network for image recognition task (MNIST dataset). The accuracy achieved shows higher
performance stability over temperature and time.
Towards the Growth of Hexagonal Boron Nitride on Ge(001)/Si Substrates by Chemical Vapor Deposition
(2022)
The growth of hexagonal boron nitride (hBN) on epitaxial Ge(001)/Si substrates via high-vacuum chemical vapor deposition from borazine is investigated for the first time in a systematic manner. The influences of the process pressure and growth temperature in the range of 10−7–10−3 mbar and 900–980 °C, respectively, are evaluated with respect to morphology, growth rate, and crystalline quality of the hBN films. At 900 °C, nanocrystalline hBN films with a lateral crystallite size of ~2–3 nm are obtained and confirmed by high-resolution transmission electron microscopy images. X-ray photoelectron spectroscopy confirms an atomic N:B ratio of 1 ± 0.1. A three-dimensional growth mode is observed by atomic force microscopy. Increasing the process pressure in the reactor mainly affects the growth rate, with only slight effects on crystalline quality and none on the principle growth mode. Growth of hBN at 980 °C increases the average crystallite size and leads to the formation of 3–10 well-oriented, vertically stacked layers of hBN on the Ge surface. Exploratory ab initio density functional theory simulations indicate that hBN edges are saturated by hydrogen, and it is proposed that partial de-saturation by H radicals produced on hot parts of the set-up is responsible for the growth
The combination of two-dimensional materials, such as graphene, with established thin films offers great opportunities for enabling next-generation vertical transistors for various applications. This paper gives a brief overview about different vertical transistor concepts using twodimensional materials proposed so far, e.g. the hot electron transistor and the Barristor. With the arrival of twodimensional materials, the hot electron transistor also experienced a revival with predicted cut-off frequencies in the THz range. The Barristor overcomes the weak current saturation of lateral graphene field-effect transistors and high on-off ratios up to 107 were demonstrated, which are suitable parameters for logic applications. By combining a
semiconductor-graphene-semiconductor design of the simplest hot electron transistor with the Barristor operating principle a new device, called graphene adjustable-barriers transistor, can be realized. This new device concept provides the potential for RF, power electronics, and optoelectronic applications.
The use of alternating current (AC) electrokinetic forces, like dielectrophoresis and AC electroosmosis, as a simple and fast method to immobilize sub-micrometer objects onto nanoelectrode arrays is presented. Due to its medical relevance, the influenza virus is chosen as a model organism. One of the outstanding features is that the immobilization of viral material to the electrodes can be achieved permanently, allowing subsequent handling independently from the electrical setup. Thus, by using merely electric fields, we demonstrate that the need of prior chemical surface modification could become obsolete. The accumulation of viral material over time is observed by fluorescence microscopy. The influences of side effects like electrothermal fluid flow, causing a fluid motion above the electrodes and causing an intensity gradient within the electrode array, are discussed. Due to the improved resolution by combining fluorescence microscopy with deconvolution, it is shown that the viral material is mainly drawn to the electrode edge and to a lesser extent to the electrode surface. Finally, areas of application for this functionalization technique are presented.
This work presents a quasi-static electrical characterization of 1-transistor-1-resistor memristive structures designed following hardness-by-design techniques integrated in the CMOS fabrication process to assure multi-level capabilities in harsh radiation environments. Modulating the gate voltage of the enclosed layout transistor connected in series with the memristive device, it was possible to achieve excellent switching capabilities from a single high resistance state to a total of eight different low resistance states (more than 3 bits). Thus, the fabricated devices are suitable for their integration in larger in-memory computing systems and in multi-level memory applications.
Index Terms—radiation-hard, hardness-by-design, memristive
devices, Enclosed Layout Transistor, in-memory computing
Analogue pattern recognition with stochastic switching binary CMOS‑integrated memristive devices
(2020)
Biological neural networks outperform todays computer technology in terms of power consumption and computing speed when associative tasks, like pattern recognition, are to be solved. The analogue and massive parallel in-memory computing in biology differs strongly with conventional transistor electronics using the von Neumann architecture. Therefore, novel bio-inspired computing architectures are recently highly investigated in the area of neuromorphic computing. Here, memristive devices, which serve as non-volatile resistive memory, are used to emulate the plastic behaviour of biological synapses. In particular, CMOS integrated resistive random access memory (RRAM) devices are promising candidates to extend conventional CMOS technology in neuromorphic systems. However, dealing with the inherent stochasticity of the resistive switching effect can be challenging for network performance. In this work, the probabilistic switching is exploited to emulate stochastic plasticity with fully CMOS integrated binary RRAM devices. Two different RRAM technologies with different device variabilities are investigated in detail and their use in a stochastic artificial neural network (StochANN) to solve the MINST pattern recognition task is examined. A mixed-signal implementation with hardware synapses and software neurons as well as numerical simulations show the proposed concept of stochastic computing is able to handle analogue data with binary memory cells.
Logic-in-memory (LiM) circuits based on resistive random access memory (RRAM) devices and the material implication logic are promising candidates for the development of low-power computing devices that could fulfill the growing demand of distributed computing systems. However, these circuits are affected by many reliability challenges that arise from device nonidealities (e.g., variability) and the characteristics of the employed circuit architecture. Thus, an accurate investigation of the variability at the array level is needed to evaluate the reliability and performance of such circuit architectures. In this work, we explore the reliability and performance of smart IMPLY (SIMPLY) (i.e., a recently proposed LiM architecture with improved reliability and performance) on two 4-kb RRAM arrays based on different resistive switching oxides integrated in the back end of line (BEOL) of the 0.25- μm BiCMOS process. We analyze the tradeoff between reliability and energy consumption of SIMPLY architecture by exploiting the results of an extensive array-level variability characterization of the two technologies. Finally, we study the worst case performance of a full adder implemented with the SIMPLY architecture and benchmark it on the analogous CMOS implementation.
A comprehensive analysis of two types of artificial neural networks (ANN) is performed to assess the influence of quantization on the synaptic weights. Conventional multilayer-perceptron (MLP) and convolutional neural networks (CNN) have been considered by changing their features in the training and inference contexts, such as number of levels in the quantization process, the number of hidden layers on the network topology, the number of neurons per hidden layer, the image databases, the number of convolutional layers, etc. A reference technology based on 1T1R structures with bipolar memristors including HfO2 dielectrics was employed, accounting for different multilevel schemes and the corresponding conductance quantization algorithms. The accuracy of the image recognition processes was studied in depth. This type of studies are essential prior to hardware implementation of neural networks. The obtained results support the use of CNNs for image domains. This is linked to the role played by convolutional layers at extracting image features and reducing the data complexity. In this case, the number of synaptic weights can be reduced in comparison to conventional MLPs.
Chronic Obstructive Pulmonary Disease (COPD) is a life-threatening lung disease and a major cause of morbidity and mortality worldwide. Although a curative therapy has yet to be found, permanent monitoring of biomarkers that reflect the disease progression plays a pivotal role for the effective management of COPD. The accurate examination of respiratory tract fluids like saliva is a promising approach for staging the disease and predicting its upcoming exacerbations in a Point-of-Care (PoC) environment. Nonetheless, this approach is only feasible by concurrent consideration of patients' demographic and medical parameters. Therefore, Machine Learning (ML) tools are necessary for the comprehensive recognition of COPD in a PoC setting. As a result, the objective of this work was to implement ML tools on the data acquired from characterizing saliva samples of COPD patients and healthy controls for classification purposes. First, a permittivity biosensor was used to characterize dielectric properties of saliva samples and, subsequently, ML tools were applied on the acquired data for classification. The XGBoost gradient boosting algorithm provided a high classification accuracy of 91.25%, making it a promising model for COPD recognition. Integration of this model on a neuromorphic chip, in the future, will enable the real-time detection of COPD in PoC, with low energy consumption and high patient privacy.
The impact of artificial intelligence on human life
has increased significantly in recent years. However, as the
complexity of problems rose aswell, increasing system features
for such amount of data computation became troublesome due
to the von Neumann’s computer architecture. Neuromorphic
computing aims to solve this problem by mimicking the parallel
computation of a human brain. For this approach, memristive
devices are used to emulate the synapses of a human brain. Yet,
common simulations of hardware based networks require time
consuming Monte-Carlo simulations to take into account the
stochastic switching of memristive devices. This work presents
an alternative concept making use of the convolution of the
probability distribution functions (PDF) of memristor currents
by its equivalent multiplication in Fourier domain. An artificial
neural network is accordingly implemented to perform the
inference stage with handwritten digits.
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. The 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.
Due to the unique electronic structures, graphene and other 2D Materials are considered as materials which can enable and extend the functionalities and performance in a large variety of applications, among them in microelectronics. At this point, the investigation and preparation of graphene devices in conditions resembling as close as possible the Si technology environment is of highest importance.Towards these goals, this paper focuses on the full spectra of graphene research aspects in 200mm pilot line. We investigated different process module developments such as CMOS compatible growth of high quality graphene on germanium and its growth mechanisms, transfer related challenges on target substrates, patterning, passivation and various concepts of contacting of graphene on a full 200 mm wafers. Finally, we fabricated proof-of-concept test structures e.g. TLM, Hall bars and capacitor structures to prove the feasibility of graphene processing in the pilot line of IHP.
Resistive switching memory (RRAM) is a promising technology for highly efficient computing scenarios. RRAM arrays enabled the acceleration of neural networks for artificial intelligence and the creation of In-Memory Computing circuits. However, the arrays are affected by several issues materializing in conductance variations that might cause severe performance degradation in those applications. Among those, one is related to the drift of the low conductance states appearing immediately at the end of program and verify algorithms that are fundamental for an accurate Multi-level conductance operation. In this work, we tackle the issue by developing an Incremental Reset and Verify technique showing enhanced variability and reliability features compared with a traditional refresh-based approach.
A key requirement for RRAM in neural network accelerators with a large number of synaptic parameters is the multilevel programming. This is hindered by resistance imprecision due to cycle-to-cycle and device-to-device variations. Here, we compare two multilevel programming algorithms to minimize resistance variations in a 4-kbit array of HfO 2 RRAM. We show that gate-based algorithms have the highest reliability. The optimized scheme is used to implement a neural network with 9-level weights, achieving 91.5% (vs. software 93.27%) in MNIST recognition.
The arrival of high-mobility two-dimensional materials like graphene leads to the renaissance of former vertical semiconductor–metal–semiconductor (SMS) hot electron transistors. Because of the monolayer thickness of graphene, improved SMS transistors with a semimetallic graphene-base electrode are now feasible for high-frequency applications. In this study we report about a device that consists of amorphous silicon, graphene, and crystalline silicon. For the first time, this device is fabricated by a four-mask lithography process which leads to significant improvements in the device performance. A strongly increased common-emitter current gain of 2% could be achieved while the on–off ratio improved to 1.6 × 105, which is already higher than predicted theoretically. This could be mainly attributed to better interface characteristics and decreased lateral dimensions of the devices. A cutoff frequency of approximately 26 MHz could be forecasted based on the DC measurements of the device.
A graphene-based three terminal barristor device was proposed to overcome the low on/off ratios and insufficient current saturation of conventional graphene field effect transistors. In this study, we fabricated and analyzed a novel graphene-based transistor, which resembles the structure of the barristor but uses a different operating condition. This new device, termed graphene adjustable-barriers transistor (GABT), utilizes a semiconductor-based gate rather than a metal−insulator gate structure to modulate the device currents. The key feature of the device is the two graphene-semiconductor Schottky barriers with different heights that are controlled simultaneously by the gate voltage. Due to the asymmetry of the barriers, the drain current exceeds the gate current by several orders of magnitude. Thus, the GABT can be considered an amplifier with an alterable current gain. In this work, a silicon−graphene−germanium GABT with an ultra-high current gain (ID/IG up to 8 × 106) was fabricated, and the device functionality was demonstrated. Additionally, a capacitance model is applied to predict the theoretical device performance resulting in an on−off ratio above 106, a swing of 87 mV/dec, and a drivecurrent of about 1 × 106 A/cm2.
Indium oxide (InxOy) thin films were deposited by plasma-enhanced atomic layer deposition (PEALD) using trimethylindium and oxygen plasma in a low-temperature range of 80–200 °C. The optical properties, chemical composition, crystallographic structure, and electrical characteristics of these layers were investigated by spectroscopic ellipsometry (SE), x-ray photoelectron spectroscopy (XPS), x-ray diffraction (XRD), as well as current-voltage and capacitance-voltage measurements. The SE results yielded a nearly constant growth rate of 0.56 Å per cycle and a thickness inhomogeneity of ≤1.2% across 4-in. substrates in the temperature range of 100–150 °C. The refractive index (at 632.8 nm) was found to be 2.07 for the films deposited at 150 °C. The PEALD-InxOy layers exhibit a direct (3.3 ± 0.2 eV) and an indirect (2.8 ± 0.1 eV) bandgap with an uptrend for both with increasing substrate temperature. Based on XPS characterization, all InxOy samples are free of carbon impurities and show a temperature-dependent off-stoichiometry indicating oxygen vacancies. XRD diffraction patterns demonstrate an onset of crystallization at 150 °C. Consistent with the optical, XPS, and XRD data, the films deposited at ≥150 °C possess higher electrical conductivity. Our findings prove that a low-temperature PEALD process of InxOy is feasible and promising for a high-quality thin-film deposition without chemical impurities on thermally fragile substrates.
An Al2O3/ZnO heterojunction was grown on a Si single crystal substrate by subsequent thermal and plasma-assisted atomic layer deposition (ALD) in situ. The band offsets of the heterointerface were then studied by consecutive removal of the layers by argon sputtering, followed by in situ X-ray photoelectron spectroscopy. The valence band maximum and conduction band minimum of Al2O3 are found to be 1.1 eV below and 2.3 eV above those of ZnO, resulting in a type-I staggered heterojunction. An apparent reduction of ZnO to elemental Zn in the interface region was detected in the Zn 2p core level and Zn L3MM Auger spectra. This suggests an interface formation different from previous models. The reduction of ZnO to Zn in the interface region accompanied by the creation of oxygen vacancies in ZnO results in an upward band bending at the interface. Therefore, this study suggests that interfacial properties such as the band bending as well as the valence and conduction band offsets should be in situ controllable to a certain extent by careful selection of the process parameters.
Mitigating the Effects of RRAM Process Variation on the Accuracy of Artifical Neural Networks
(2022)
Weight storage is a key challenge in the efficient implementation of artificial neural networks. Novel memory technologies such as RRAM are able to greatly improve density and introduce non-volatility and multibit capabilities to this component of ANN accelerators. The usage of RRAM in this domain comes with downsides, mainly caused by cycle-to-cycle and device-to-device variability leading to erroneous readouts, greatly affecting digital systems. ANNs have the ability to compensate for this by their inherent redundancy and usually exhibit a gradual deterioration in the accuracy of the task at hand. This means, that slight error rates can be acceptable for weight storage in an ANN accelerator. In this work we link device-to-device variability to the accuracy of an ANN for such an accelerator. From this study, we can estimate how strongly a certain net is affected by a certain device parameter variability. This methodology is then used to present three mitigation strategies and to evaluate how they affect the reaction of the network to variability: a) Dropout Layers b) Fault-Aware Training c) Redundancy. These mitigations are then evaluated by their ability to improve accuracy and to lower hardware overhead by providing data for a real-word example. We improved this network’s resilience in such a way that it could tolerate double the variation in one of the device parameters (standard deviation of the oxide thickness can be 0.4 nm instead of 0.2 nm while maintaining sufficient accuracy.)