Publisher's Note: “The building blocks of a brain-inspired computer” [Appl. Phys. Rev. <b>7</b>, 011305 (2020)]

Kendall, Jack D.; Kumar, Suhas

doi:10.1063/5.0005782

Cited by 20 publications

(27 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[126] Collaborations should be expanded to include researchers in solid-state physics, materials science, nanoelectronics, circuit/architecture design, and information theory. Memristors show great promise to be a fabric for producing brain-inspired building blocks, [127] and this progress report showcases different types of memristor-based applications. Memristor technologies are versatile enough to Figure 13.…”

Section: Discussionmentioning

confidence: 87%

Memristors—From In‐Memory Computing, Deep Learning Acceleration, and Spiking Neural Networks to the Future of Neuromorphic and Bio‐Inspired Computing

Mehonić¹,

Sebastian

Rajendran

et al. 2020

Advanced Intelligent Systems

183

121

View full text Add to dashboard Cite

Three factors are currently driving the main developments in artificial intelligence (AI): availability of vast amounts of data, continuous growth in computing power, and algorithmic innovations. Graphics processing units (GPUs) have been demonstrated as effective co-processors for the implementation of machine learning (ML) algorithms based on deep learning (DL). Solutions based on DL and GPU implementations have led to massive improvements in many AI tasks, but have also caused an exponential increase in demand for computing power. Recent analyses show that the demand for computing power has increased by a factor of 300 000 since 2012, and the estimate is that this demand will double every 3.4 months-at a much faster rate than improvements made historically through Moore's scaling (a sevenfold improvement over the same period of time). [1] At the same time, Moore's law has been slowing down significantly for the last few years, [2] as there are strong indications that we will not be able to continue scaling down complementary metal-oxide-semiconductor (CMOS) transistors. This calls for the exploration of alternative technology roadmaps for the development of scalable and efficient AI solutions. Transistor scaling is not the only way to improve computing performance. Architectural innovations, such as GPUs, field-programmable arrays (FPGAs), and application-specific integrated circuits (ASICs), have all significantly advanced the ML field. [3] A common aspect of modern computing architectures for ML is a move away from the classical von-Neumann architecture that physically separates memory and computing. This approach yields a performance bottleneck that is often the main reason for both energy and speed inefficiency of ML implementations on conventional hardware platforms due to

show abstract

Section: Discussionmentioning

confidence: 87%

Memristors—From In‐Memory Computing, Deep Learning Acceleration, and Spiking Neural Networks to the Future of Neuromorphic and Bio‐Inspired Computing

Mehonić¹,

Sebastian

Rajendran

et al. 2020

Advanced Intelligent Systems

183

121

View full text Add to dashboard Cite

show abstract

“…Traditional von Neumann based computing architecture is inefficient and energy-hungry for such data-driven tasks. Non-volatile IMC technique becomes an ideal choice for machine learning because synaptic weights can be mapped to 2D memory crossbar arrays to perform parallel computing with the input signal, [42] which greatly improves the processing efficiency of the hardware system. Different neural network models such as convolutional neural networks, [27,43] long shortterm memory networks, [44] deep neural networks, [45,46] and reservoir computing [8] have been implemented with IMC architecture.…”

Section: Machine Learningmentioning

confidence: 99%

“…Another promising application is brain-inspired computing, [42,56] which aims to build a brain-like information processing system that can simultaneously possess both memory and learning capabilities. The human brain is a complicated neural network composed of more than 10 11 neurons and 10 15 synapses.…”

Section: Brain-inspired Computingmentioning

confidence: 99%

Functional Applications of Future Data Storage Devices

Yang

Zhou

Han

2021

Adv Elect Materials

View full text Add to dashboard Cite

traditional computing systems. Strategies like adopting multiple levels of cache, [3] increasing memory bandwidth, [4] and near-memory computing [5] have been proposed to alleviate this problem which yet still seem to be insufficient to meet the increasing computing demands.In-memory computing (IMC) which refers to the realization of computational tasks within the memory unit aims to reduce the frequent movement of data across the bus (Figure 1b), providing new insights for building highly efficient computing systems. IMC with function of parallel computation, reducing either the computational complexity or accessed amount of data effectively can be performed on both volatile and non-volatile memories. IMC has a wide range of applications, ranging from stochastic computing that requires randomness and low precision to scientific computing with high precision. Volatile memories including static randomaccess memory (SRAM) and dynamic random-access memory (DRAM) have been mainly utilized to execute Boolean functions and obtained dozens of times speedup in compute-heavy as well as low input-output movement applications compared with conventional architectures in which SRAM and DRAM were only used for data storage. [6] While nonvolatile memory including Flash and emerging memristive devices (resistive random-access memory [RRAM], phase-change memory [PCM], and magnetic random-access memory [MRAM], etc.) with the ability to store a continuous conductance state were proved to perform matrix-vector multiplication (MVM) for parallel IMC based on Ohm's law and Kirchhoff's law. [7] Especially, the memristive device with crossbar configuration can be directly integrated with high density local interconnects and low thermal burden, allowing the significant boost to IMC performance.This review provides an overview of related work in various memory techniques, their applications, and required parameters in IMC, the current state of the art, and evaluation metrics and highlights opportunities for further development. The Development of Memory TechnologiesDepending on the state of the data being stored, current memory technologies fall into two categories (Figure 2a): volatile and nonvolatile. Volatile memories will lose the data preserved when the power is disconnected, mainly including SRAM and DRAM, while information in nonvolatile memories including read-only memory (ROM), hard disk driver (HDD), Flash, MRAM, PCM, RRAM, and ferroelectric random-accessThe development of artificial intelligence and big data analytics is driving a revolution in methods for data processing and storage. Confronting speed and energy consumption issues, these fields require new computing systems to parallelly retrieve, process, and store massive amounts of data. Beyond CMOS devices and technology, advances in data storage technology such as static random-access memory, dynamic random-access memory, flash memories, resistive memories, phase change memories, and magnetic memories have made functional computing possible. In this article, a broad overvi...

show abstract

“…

…”

mentioning

confidence: 99%

Organic Synaptic Diodes Based on Polymeric Mixed Ionic‐Electronic Conductors

Gärisch

Ligorio

Klein

et al. 2021

Adv Elect Materials

View full text Add to dashboard Cite

The rapid evolution of artificial intelligence-well established at the software level-is pushing the development of devices able to integrate-at the hardware level-the learning capability of biological nervous systems. [1][2][3] In order to reproduce the functionalities of biological neural networks-based on neurons interconnected through synapses [4] -these systems are mimicked in the form of artificial neural networks (ANNs). Neuromorphic devices serve as building blocks for ANNs, by operating as artificial neurons or synapses. Since the signal transfer across the biological synapse is modulated by ion dynamics, a biomimetic artificial synapse would therefore benefit from imitating this behavior.This approach has previously been explored and reported in literature, employing mainly transistor-based architectures. There, the conductivity is mediated by ionic doping of the transistor channel. [5,6] While these devices display a variety of neuromorphic functionalities, their architecture is based on three-terminal devices. This approach not only impedes dense integration into ANNs-in the form of crossbar arrays [7] -but also breaks with the biomimetic principle, as the synapse is inherently two-terminal. Thus, an equally twoterminal synaptic device would be preferable and various concepts have been presented in literature. These devices are based on metallic filament formation, [8][9][10] phase change, [11,12] spin state, [13,14] ferroelectric effects, [15,16] redox chemistry, [17] or biomembranes. [18,19] In this work, we propose to add another mechanism-inspired by the ion-based operating principle of the biological synapse-by revisiting a concept for a wholly different category of device. Although not for neuromorphic applications, controlling the electronic properties of a two-terminal device through dynamic polarization of ions has previously been employed in light-emitting electrochemical cells (LECs). [20,21] In such a device, a single layer, based on an organic mixed ionic-electronic conductor-mixed with a salt-is sandwiched between two electrodes. Upon applying a bias, the salt dissociates and ions drift toward the electrodes, resulting in the formation of electric double layers at the electrode interfaces. [22][23][24][25] This allows for improved carrier injection without the need of additional injection or transport layers and upon balanced Neuromorphic devices are likely to be the next evolution of computing, allowing to implement machine learning within hardware components. In biological neural systems, learning and signal processing are achieved by communication between neurons through time-dependent ion flux in the synapses. Integrating such ion-mediated operating principles in neuromorphic devices can deliver an energy efficient and powerful technology. Here a device known as a light-emitting electrochemical cell is revisited and modified, exploiting its ability to modulate current through ion accumulation/depletion at the electrodes and turn it into an organic synaptic diode. This two-terminal de...

show abstract

Publisher's Note: “The building blocks of a brain-inspired computer” [Appl. Phys. Rev. 7, 011305 (2020)]

Cited by 20 publications

References 0 publications

Memristors—From In‐Memory Computing, Deep Learning Acceleration, and Spiking Neural Networks to the Future of Neuromorphic and Bio‐Inspired Computing

Memristors—From In‐Memory Computing, Deep Learning Acceleration, and Spiking Neural Networks to the Future of Neuromorphic and Bio‐Inspired Computing

Functional Applications of Future Data Storage Devices

Organic Synaptic Diodes Based on Polymeric Mixed Ionic‐Electronic Conductors

Contact Info

Product

Resources

About