Electrochemical RAM

Last updated

Electrochemical Random-Access Memory (ECRAM) is a type of non-volatile memory (NVM) with multiple levels per cell (MLC) designed for deep learning analog acceleration. [1] [2] [3] An ECRAM cell is a three-terminal device composed of a conductive channel, an insulating electrolyte, an ionic reservoir, and metal contacts. The resistance of the channel is modulated by ionic exchange at the interface between the channel and the electrolyte upon application of an electric field. The charge-transfer process allows both for state retention in the absence of applied power, and for programming of multiple distinct levels, both differentiating ECRAM operation from that of a field-effect transistor (FET). The write operation is deterministic and can result in symmetrical potentiation and depression, making ECRAM arrays attractive for acting as artificial synaptic weights in physical implementations of artificial neural networks (ANN). The technological challenges include open circuit potential (OCP) and semiconductor foundry compatibility associated with energy materials. Universities, government laboratories, and corporate research teams have contributed to the development of ECRAM for analog computing. Notably, Sandia National Laboratories designed a lithium-based cell inspired by solid-state battery materials, [4] Stanford University built an organic proton-based cell, [5] and International Business Machines (IBM) demonstrated in-memory selector-free parallel programming for a logistic regression task in an array of metal-oxide ECRAM designed for insertion in the back end of line (BEOL). [6] In 2022, researchers at Massachusetts Institute of Technology built an inorganic, CMOS-compatible protonic technology that achieved near-ideal modulation characteristics using nanosecond fast pulses [7]

Contents

Operation

ECRAM synaptic cell layout and operating principle ECRAM electrochemical synaptic cell.png
ECRAM synaptic cell layout and operating principle

Write

Stress to the gate, relative to channel electrodes, can be applied in the form of fixed current or bias, driving ions toward - or away from - the electrolyte/channel interface where charge transfer occurs with free carriers. Upon insertion in the channel, the ionic charge is neutralized and the atomic species intercalate or bind to the conductive host matrix, in some cases yielding strain and localized phase transformation. Such reversible processes are equivalent to anodic/cathodic reactions in battery cells or electrochromic devices. Although in ECRAM, the programming of the memory element is defined not as a change in capacity or opacity, but by a change of channel conductivity associated with atomic species being inserted or removed as a result of the stress signal.

Read

The read operation is decoupled from the write operation thanks to the presence of three electrodes, therefore limiting read disturb. A small bias is applied between the channel electrodes, with the resulting read current being proportional to the channel conductivity, hence sensing the programmed state of the device.

Speed

The programming speed of ECRAM cells is not limited by the bulk diffusion of ions. They indeed only need to cross the interface plane between the electrolyte and the channel to induce a change in conductivity. Nanosecond write pulses can indeed trigger programming. [8] Trade-offs between gate capacitance, electronic conductivity, etc., can yield settling transients, limiting the maximum read-write frequency. [9]

Arrays

ECRAM arrays are integrated in a pseudo-crossbar layout, the gate access line being common to all devices in a row or column. If a change in electrochemical potential, the driving force of a battery, occurs upon ionic exchange between channel and gate electrode, an open circuit potential (OCP) exists at the gate contact and will differ device to device depending on the programmed state. To prevent cross-talk between cells sharing a gate line, an access device to isolate each one is added in series with the memory element. [10] Suppressing OCP in the ECRAM design, minimizes the cell size/complexity, allowing for selector-free parallel read/programming of device arrays. [6]

Synaptic function

(Left) Illustration of analog matrix-vector multiply operation in a pseudo-crossbar ecram array. (Right) Illustration of the programming of 50 distinct and reversible states in the ecram synaptic cell. ECRAM synapse in-memory compute.png
(Left) Illustration of analog matrix-vector multiply operation in a pseudo-crossbar ecram array. (Right) Illustration of the programming of 50 distinct and reversible states in the ecram synaptic cell.

Principle

Non-volatile memory (NVM) can be leveraged for in-memory compute, thereby reducing the frequency of data transfer between storage and processing units. This can ultimately improve compute time and energy efficiency over hierarchical system architectures by eliminating the Von Neumann bottleneck. Hence, when using multi-level cells (MLC) at the nodes of cross-bar arrays, one can perform analog operations on time or voltage encoded data such as vector (row input signal) × matrix (memory array) multiply. Following Kirchhoff's and Ohm's laws, the resulting vector is then obtained by integrating the current collected at each column. For ECRAM cells, an additional line is added at each row to write the cells during programming cycles, thereby yielding a pseudo-crossbar architecture. In the field of artificial intelligence (AI), deep neural networks (DNN) are used for classification and learning tasks, relying on a large number of matrix-multiply operations. Therefore, analog compute with NVM technology for such tasks are extremely attractive. ECRAM cells are uniquely positioned for use in analog deep learning accelerators due to their inherent deterministic and symmetric programming nature when compared to other devices such as resistive RAM (ReRAM or RRAM) and phase-change memory (PCM).

Requirements

MetricUnitNVM synaptic
cell target [11]
G range nS 9-72
on/off ration.a.8
# of statesn.a.1000
up/down asymmetry %5
write time ns 1

Physical implementation of artificial neural networks (ANN) must perform at iso-accuracy when benchmarked against floating point precision weights in software. This sets the boundary for device properties needed for analog deep learning accelerators. In the design of their resisistive processing unit (RPU), IBM Research has published such requirements, [11] a subset of which is listed here. Algorithm and hardware co-design can relax them somewhat but not without other trade-offs. [12]

NVM use as synaptic weights in lieu of storage implies significantly different requirements when it comes to target resistance range, number of levels, and programming speed and symmetry. Because the in-memory computation occurs in parallel through the array, many devices are addressed concurrently and therefore need to have a high average resistance to limit energy dissipation. To perform high-accuracy computation and be resilient to noise, the NVM cell needs a large number of distinct states. The programming time needs only to be fast between levels, not from the highest to the lowest resistance states. During each programming cycle (back-propagation), weight updates can be negative or positive, and the up/down traces therefore need symmetry to allow learning algorithms to converge. All NVM technologies do struggle with these targets. ECRAM individual cells can meet such stringent metrics, [6] but also need to demonstrate high-density array yield and stochasticity.

Demos with ECRAM Synaptic Arrays

Sandia National Laboratories

As reported in a 2019 publication in Science, by Elliot J. Fuller, Alec A. Talin, et al. from Sandia National Laboratories, in collaboration with Stanford University, and the University of Massachusetts Amherst: [10]

Using co-planar organic multilevel cells, isolated by conductive bridge memory (CBM) devices, the team demonstrates parallel programming and addressing in up to 3×3 arrays. In particular a 2-layer neural network is mapped to the array by transferring the weights necessary to perform an inference task resulting in a XOR operation on the binary input vector.

Individual cells are shown to have the following properties (not all achieved in the same device configuration); speed = 1 MHz read-write cycles, number of states > 50 (tunable), resistance range = 50-100 nS (tunable), endurance > 108 write ops, size = 50×50 μm2.

IBM Research

As reported in a 2019 proceeding of the IEEE International Electron Device Meeting (IEDM), by Seyoung Kim, John Rozen, et al. from IBM Research: [6]

Using metal-oxide ECRAM cells, selector-free, the team demonstrates parallel programming and addressing in 2×2 arrays. In particular, a logistic regression task is performed in-memory with 1,000 2×1 vectors as training set. 2D curve fit is achieved in a dozen epochs.

Individual cells are shown to have the following properties (not all achieved in the same device configuration); speed = 10 ns write pulses, number of states > 1,000 (tunable), resistance range = 0-50 μS (tunable), endurance > 107 write ops, size < 1×1 μm2.

Cell implementations

Various institutions have demonstrated ECRAM cells with vastly different materials, layouts, and performances.
An example set for discrete cells is listed in the table.

IonChannelDevice SizeWrite Pulse LengthReference
Li+
WO
3		100 x 100 nm25 ns [8]
Li+
Li
1−xCO
2		~1 mm20.5 s [4]
Li+
Graphene36 μm210 ms [13]
Li+
α-MO
3		~1 mm210 ms [14]
H+
PEDOT:PSS0.001 mm25 ms [5]
H+
WO
3		0.05 mm25 ms [15]
H+
WO
3		0.025 mm2210 ms [16]
H+
WO
3		0.01 mm20.1 s [17]
H+2D MXene100 µm2200 ns [18]

Li-ECRAM

Based on lithium ions, Li-ECRAM devices have demonstrated repeatable and controlled switching by applying known materials from battery technology to the memory design. [4] [13] [14] Consequently, such cells can exhibit an OCP which varies over several volts, depending on the programmed state.

H-ECRAM

Based on hydrogen ions, H-ECRAM devices have proven fast, necessitating small driving forces to induce programming. [5] [15] [16] High diffusion coefficients in various materials can be accompanied by lack of retention within the memory cell, impacting endurance. Most H-ECRAM designs use liquid and/or organic electrolytes. In a 2022 study, researchers at Massachusetts Institute of Technology demonstrated a CMOS-compatible technology based on phosphosilicate glass electrolyte that achieved ultrafast modulation characteristics with high energy efficiency. [7] The same year researchers at the Royal Institute of Technology KTH showed ECRAMS based on hydrogen intercalation into the 2D material MXene, marking the first demonstration of high speed 2D ECRAMs. [18]

MO-ECRAM

Metal-oxide based ECRAM, are inspired from OxRam materials and high-k/metal gate technology used in commercial semiconductor offerings. MO-ECRAM do enable negligible OCP and sub-μs write operations. [6]

VLSI

Processed 200mm si wafer 200mm Si Wafer.png
Processed 200mm si wafer

For advanced semiconductor memory or compute applications, a technology needs to be compatible with very large scale integration (VLSI). This puts constraints on materials used, and the techniques employed to fabricate functional devices. The implications for ECRAM are described here.

Semiconductor foundry

A semiconductor foundry can handle several technologies and has strict rules when it comes to materials being introduced in its expensive toolset to avoid cross-contamination and loss of device yield. In particular, metallic mobile ions, if present in active areas, can induce device drift and affect reliability. There are several other considerations for the foundries; including safety, cost, volume, etc. Hence, lithium ion-based Li-ECRAM faces unique challenges beyond the presence of OCP.

Back end of line (BEOL)

Memory arrays require logic periphery to operate and interface with the rest of the compute system. Such periphery is based on field-effect transistors (FETs) built on the surface of silicon wafer substrates with a high thermal budget at the front end of line (FEOL). Memory cells can be inserted between upper metal levels at back end of line (BEOL) but will still need to remain unaffected by temperatures up to ~400 °C used in subsequent steps. Together with high density patterning challenges, these restrictions make organic devices unsuitable for such integration. The ECRAMs based on 2D MXene materials [18] have shown the potential to be unaffected by 400 °C heating, but additional development is needed for the integration of ion conductors.

Heterogeneous integration (HI)

One way to introduce novel memory materials can be to use heterogeneous integration (HI) where the device array is fabricated independently from the logic controls and then bonded to the FET-containing chip to enable its use as high bandwidth memory (HBM). However, the cost and complexity associated with such scheme negatively affects the value proposition for displacing existing memory technologies.

Related Research Articles

<span class="mw-page-title-main">Dendrite</span> Small projection on a neuron that receives signals

A dendrite or dendron is a branched protoplasmic extension of a nerve cell that propagates the electrochemical stimulation received from other neural cells to the cell body, or soma, of the neuron from which the dendrites project. Electrical stimulation is transmitted onto dendrites by upstream neurons via synapses which are located at various points throughout the dendritic tree.

An artificial neuron is a mathematical function conceived as a model of biological neurons, a neural network. Artificial neurons are elementary units in an artificial neural network. The artificial neuron receives one or more inputs and sums them to produce an output. Usually each input is separately weighted, and the sum is passed through a non-linear function known as an activation function or transfer function. The transfer functions usually have a sigmoid shape, but they may also take the form of other non-linear functions, piecewise linear functions, or step functions. They are also often monotonically increasing, continuous, differentiable and bounded. Non-monotonic, unbounded and oscillating activation functions with multiple zeros that outperform sigmoidal and ReLU like activation functions on many tasks have also been recently explored. The thresholding function has inspired building logic gates referred to as threshold logic; applicable to building logic circuits resembling brain processing. For example, new devices such as memristors have been extensively used to develop such logic in recent times.

In neuroscience, synaptic plasticity is the ability of synapses to strengthen or weaken over time, in response to increases or decreases in their activity. Since memories are postulated to be represented by vastly interconnected neural circuits in the brain, synaptic plasticity is one of the important neurochemical foundations of learning and memory.

Neuromorphic computing is an approach to computing that is inspired by the structure and function of the human brain. A neuromorphic computer/chip is any device that uses physical artificial neurons to do computations. In recent times, the term neuromorphic has been used to describe analog, digital, mixed-mode analog/digital VLSI, and software systems that implement models of neural systems. The implementation of neuromorphic computing on the hardware level can be realized by oxide-based memristors, spintronic memories, threshold switches, transistors, among others. Training software-based neuromorphic systems of spiking neural networks can be achieved using error backpropagation, e.g., using Python based frameworks such as snnTorch, or using canonical learning rules from the biological learning literature, e.g., using BindsNet.

<span class="mw-page-title-main">Carver Mead</span> American scientist and engineer

Carver Andress Mead is an American scientist and engineer. He currently holds the position of Gordon and Betty Moore Professor Emeritus of Engineering and Applied Science at the California Institute of Technology (Caltech), having taught there for over 40 years. He taught Deborah Chung, the first female engineering graduate of Caltech. He advised the first female electrical engineering student at Caltech, Louise Kirkbride. His contributions as a teacher include the classic textbook Introduction to VLSI Systems (1980), which he coauthored with Lynn Conway.

<span class="mw-page-title-main">Optical neural network</span>

An optical neural network is a physical implementation of an artificial neural network with optical components. Early optical neural networks used a photorefractive Volume hologram to interconnect arrays of input neurons to arrays of output with synaptic weights in proportion to the multiplexed hologram's strength. Volume holograms were further multiplexed using spectral hole burning to add one dimension of wavelength to space to achieve four dimensional interconnects of two dimensional arrays of neural inputs and outputs. This research led to extensive research on alternative methods using the strength of the optical interconnect for implementing neuronal communications.

<span class="mw-page-title-main">Neural circuit</span> Network or circuit of neurons

A neural circuit is a population of neurons interconnected by synapses to carry out a specific function when activated. Multiple neural circuits interconnect with one another to form large scale brain networks.

Unconventional computing is computing by any of a wide range of new or unusual methods. It is also known as alternative computing.

Resistive random-access memory is a type of non-volatile (NV) random-access (RAM) computer memory that works by changing the resistance across a dielectric solid-state material, often referred to as a memristor.

Cellular neuroscience is a branch of neuroscience concerned with the study of neurons at a cellular level. This includes morphology and physiological properties of single neurons. Several techniques such as intracellular recording, patch-clamp, and voltage-clamp technique, pharmacology, confocal imaging, molecular biology, two photon laser scanning microscopy and Ca2+ imaging have been used to study activity at the cellular level. Cellular neuroscience examines the various types of neurons, the functions of different neurons, the influence of neurons upon each other, and how neurons work together.

<span class="mw-page-title-main">Nonsynaptic plasticity</span> Form of neuroplasticity

Nonsynaptic plasticity is a form of neuroplasticity that involves modification of ion channel function in the axon, dendrites, and cell body that results in specific changes in the integration of excitatory postsynaptic potentials and inhibitory postsynaptic potentials. Nonsynaptic plasticity is a modification of the intrinsic excitability of the neuron. It interacts with synaptic plasticity, but it is considered a separate entity from synaptic plasticity. Intrinsic modification of the electrical properties of neurons plays a role in many aspects of plasticity from homeostatic plasticity to learning and memory itself. Nonsynaptic plasticity affects synaptic integration, subthreshold propagation, spike generation, and other fundamental mechanisms of neurons at the cellular level. These individual neuronal alterations can result in changes in higher brain function, especially learning and memory. However, as an emerging field in neuroscience, much of the knowledge about nonsynaptic plasticity is uncertain and still requires further investigation to better define its role in brain function and behavior.

A physical neural network is a type of artificial neural network in which an electrically adjustable material is used to emulate the function of a neural synapse or a higher-order (dendritic) neuron model. "Physical" neural network is used to emphasize the reliance on physical hardware used to emulate neurons as opposed to software-based approaches. More generally the term is applicable to other artificial neural networks in which a memristor or other electrically adjustable resistance material is used to emulate a neural synapse.

Paul Richard Adams, FRS is a neuroscientist currently serving as a Professor in the Department of Neurobiology and Behavior at Stony Brook University in New York.

NOMFET is a nanoparticle organic memory field-effect transistor. The transistor is designed to mimic the feature of the human synapse known as plasticity, or the variation of the speed and strength of the signal going from neuron to neuron. The device uses gold nano-particles of about 5—20 nm set with pentacene to emulate the change in voltages and speed within the signal. This device uses charge trapping/detrapping in an array of gold nanoparticles (NPs) at the SiO2/pentacene interface to design a SYNAPSTOR (synapse transistor) mimicking the dynamic plasticity of a biological synapse. This device (memristor-like) mimics short-term plasticity (STP) and temporal correlation plasticity (STDP, spike-timing dependent plasticity), two "functions" at the basis of learning processes. A compact model was developed, and these organic synapstors were used to demonstrate an associative memory, which can be trained to present a pavlovian response. A recent report showed that these organic synapse-transistors (synapstor) are working at 1 volt and with a plasticity typical response time in the range 100-200 ms. The device also works in contact with an electrolyte (EGOS : electrolyte gated organic synapstor) and can be interfaced with biologic neurons.

<span class="mw-page-title-main">SyNAPSE</span> DARPA program

SyNAPSE is a DARPA program that aims to develop electronic neuromorphic machine technology, an attempt to build a new kind of cognitive computer with form, function, and architecture similar to the mammalian brain. Such artificial brains would be used in robots whose intelligence would scale with the size of the neural system in terms of the total number of neurons and synapses and their connectivity.

Kwabena Adu Boahen is a Professor of Bioengineering and Electrical Engineering at Stanford University. He previously taught at the University of Pennsylvania.

A synaptic transistor is an electrical device that can learn in ways similar to a neural synapse. It optimizes its own properties for the functions it has carried out in the past. The device mimics the behavior of the property of neurons called spike-timing-dependent plasticity, or STDP.

The organic electrochemical transistor (OECT) is an organic electronic device which functions like a transistor. The current flowing through the device is controlled by the exchange of ions between an electrolyte and the OECT channel composed of an organic conductor or semiconductor. The exchange of ions is driven by a voltage applied to the gate electrode which is in ionic contact with the channel through the electrolyte. The migration of ions between the channel and the electrolyte is accompanied by electrochemical redox reactions occurring in the channel material. The electrochemical redox of the channel along with ion migration changes the conductivity of the channel in a process called electrochemical doping. OECTs are being explored for applications in biosensors, bioelectronics and large-area, low-cost electronics. OECTs can also be used as multi-bit memory devices that mimic the synaptic functionalities of the brain. For this reason, OECTs can be also being investigated as elements in neuromorphic computing applications.

The memtransistor is an experimental multi-terminal passive electronic component that might be used in the construction of artificial neural networks. It is a combination of the memristor and transistor technology. This technology is different from the 1T-1R approach since the devices are merged into one single entity. Multiple memristers can be embedded with a single transistor, enabling it to more accurately model a neuron with its multiple synaptic connections. A neural network produced from these would provide hardware-based artificial intelligence with a good foundation.

<span class="mw-page-title-main">Jennifer Rupp</span> German-American professor

Jennifer L. M. Rupp FRSC is a material scientist and professor at the Technical University of Munich, visiting professor at the Massachusetts Institute of Technology and the CTO for battery research at TUM International Energy Research. Rupp has published more than 115 papers in peer reviewed journals, co-authored 7 book chapters and holds more than 25 patents. Rupp research broadly encompasses solid state materials and cell designs for sustainable batteries, energy conversion and neuromorphic memory and computing.

References

  1. ↑ Shi, J.; Ha, S. D.; Zhou, Y.; Schoofs, F.; Ramanathan, S. (2013). "A correlated nickelate synaptic transistor". Nature Communications. 4: 2676. Bibcode:2013NatCo...4.2676S. doi: 10.1038/ncomms3676 . PMID   24177330.
  2. ↑ Tang, Jianshi; Bishop, Douglas; Kim, Seyoung; Copel, Matt; Gokmen, Tayfun; Todorov, Teodor; Shin, SangHoon; Lee, Ko-Tao; Solomon, Paul (2018-12-01). "ECRAM as Scalable Synaptic Cell for High-Speed, Low-Power Neuromorphic Computing". 2018 IEEE International Electron Devices Meeting (IEDM). pp. 13.1.1–4. doi:10.1109/IEDM.2018.8614551. ISBN   978-1-7281-1987-8. S2CID   58674536 . Retrieved 2020-07-16.
  3. ↑ "Finite element modeling of electrochemical random access memory - iis-projects". iis-projects.ee.ethz.ch. Zürich, Switzerland: ETH Zurich . Retrieved 2020-07-16.
  4. 1 2 3 'E. J. Fuller et al., Adv. Mater., 29, 1604310 (2017)
  5. 1 2 3 Y. van de Burgt et al., Nature Electronics, 1, 386 (2018)
  6. 1 2 3 4 5 Kim, S. (2019). "Metal-oxide based, CMOS-compatible ECRAM for Deep Learning Accelerator". 2019 IEEE International Electron Devices Meeting (IEDM). pp. 35.7.1–4. doi:10.1109/IEDM19573.2019.8993463. ISBN   978-1-7281-4032-2. S2CID   211211273.
  7. 1 2 Onen, Murat; Emond, Nicolas; Wang, Baoming; Zhang, Difei; Ross, Frances M.; Li, Ju; Yildiz, Bilge; del Alamo, Jesús A. (29 July 2022). "Nanosecond protonic programmable resistors for analog deep learning" . Science. 377 (6605): 539–543. doi:10.1126/science.abp8064. ISSN   0036-8075. PMID   35901152. S2CID   251159631.
  8. 1 2 Tang, J. (2018). "ECRAM as Scalable Synaptic Cell for High-Speed, Low-Power Neuromorphic Computing". 2018 IEEE International Electron Devices Meeting (IEDM). pp. 13.1.1–4. doi:10.1109/IEDM.2018.8614551. ISBN   978-1-7281-1987-8. S2CID   58674536.
  9. ↑ D. Bishop et al., proceedings of the international conference in Solid-State Devices and Materials (SSDM), pp. 23-24 (2018)
  10. 1 2 Fuller, E.J.; Keene, S.T.; Melianas, A.; Wang, Z.; Agarwal, S.; Li, Y.; Tuchman, Y.; James, C.D.; Marinella, M.J.; Yang, J.J.; Salleo, A.; Talin, A.A. (2019). "Parallel programming of an ionic floating-gate memory array for scalable neuromorphic computing". Science. 364 (6440): 570–4. Bibcode:2019Sci...364..570F. doi: 10.1126/science.aaw5581 . PMID   31023890. S2CID   133605392.
  11. 1 2 Tayfun, G.; Yurii, V. (2016). "Acceleration of Deep Neural Network Training with Resistive Cross-Point Devices: Design Considerations". Frontiers in Neuroscience. 10: 333. doi: 10.3389/fnins.2016.00333 . PMC   4954855 . PMID   27493624.
  12. ↑ Tayfun, G.; Haensch, H. (2020). "Algorithm for Training Neural Networks on Resistive Device Arrays". Frontiers in Neuroscience. 14: 103. doi: 10.3389/fnins.2020.00103 . PMC   7054461 . PMID   32174807.
  13. 1 2 Sharbati, M.T.; Du, Y.; Torres, J.; Ardolino, N.D.; Yun, M.; Xiong, F. (2018). "Artificial Synapses: Low-Power, Electrochemically Tunable Graphene Synapses for Neuromorphic Computing". Adv. Mater. 30: 1870273. doi: 10.1002/adma.201870273 .
  14. 1 2 Yang, C.-S.; Shang, D.-S.; Liu, N.; Fuller, E.J.; Agrawal, S.; Alec Talin, A.; Li, Y.-Q.; Shen, B.-G.; Sun, Y. (2018). "All-Solid-State Synaptic Transistor with Ultralow Conductance for Neuromorphic Computing". Adv. Funct. Mater. 28 (42): 1804170. doi:10.1002/adfm.201804170. OSTI   1472248. S2CID   104934211.
  15. 1 2 Yao, X.; Klyukin, K.; Lu, W. (2020). "Protonic solid-state electrochemical synapse for physical neural networks". Nat Commun. 11 (1): 3134. Bibcode:2020NatCo..11.3134Y. doi:10.1038/s41467-020-16866-6. PMC   7371700 . PMID   32561717.
  16. 1 2 Yang, J.-T.; Ge, C.; Du, J.-Y.; Huang, H.-Y.; He, M.; Wang, C.; Lu, H.-B.; Yang, G.-Z.; Jin, K.-J. (2018). "Artificial Synapses Emulated by an Electrolyte-Gated Tungsten-Oxide Transistor". Adv. Mater. 30 (34): 1801548. doi:10.1002/adma.201801548. PMID   29974526. S2CID   49655665.
  17. ↑ J. Lee et al., proceedings of the IEEE international Silicon Nanoelectronics Workshop (SNW), pp. 31-32 (2018)
  18. 1 2 3 Melianas, Armantas; Kang, Min‐A; VahidMohammadi, Armin; Quill, Tyler James; Tian, Weiqian; Gogotsi, Yury; Salleo, Alberto; Hamedi, Mahiar Max (March 2022). "High‐Speed Ionic Synaptic Memory Based on 2D Titanium Carbide MXene". Advanced Functional Materials. 32 (12): 2109970. doi: 10.1002/adfm.202109970 . ISSN   1616-301X. S2CID   244484634.


This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.