The world of electronics and computation is at a critical crossroads now. This has been precipitated by the end of Moore's law and the rapid emergence of AI/ML. Technological applications, such as robotics, automated systems that replicate human functions including driving vehicles, and pattern recognitions based on visual, audio, touch, and even smell, are rapidly transforming the way we live. Since there has been a tremendous demand for computing systems with the capability of handling huge amount of data and performing human-like decisions, one needs to pause and re-examine the way computation is done today. Clearly, von Neuman limited CMOS technology is not best suited to replicate human-like computing, and one needs to look at other novel options for the emerging field of brain-like electronics (Fig. 1). Memristors, which enable brain inspired electronics, have seen a rapid growth in popularity recently.

FIG. 1.

Exponential growth of publications in the field of memristors (from Clarivariate).

FIG. 1.

Exponential growth of publications in the field of memristors (from Clarivariate).

Close modal

This collection of reviews is our initial attempt to get the key players in this field to address this exciting frontier. We requested the authors to not only go beyond a conservative review but also take some risks in projecting the future. We were extremely pleased to get a dozen outstanding reviews in a variety of emerging areas as detailed below.

The brain is a natural computer that outperforms our best computers in solving certain problems such as instantly identifying faces or understanding natural language. This realization has led to a flurry of research into neuromorphic or brain-inspired computing that has shown promise for enhanced computing capabilities. The review by Kendall and Kumar1 points to the important primitives of a brain-inspired computer that could drive another decade-long wave of computer engineering. The need to enable smarter and intelligent computing platforms at a low area and energy cost has brought forth interesting avenues for exploiting nonvolatile memory (NVM) technologies. Chakraborty and his team2 focus on nonvolatile memory technologies and their applications to bio-inspired neuromorphic computing, enabling spike-based machine intelligence.

As artificial intelligence calls for novel energy-efficient hardware, neuromorphic computing systems based on analog resistive switching memory (RSM) featured by a continuous and controllable conductance-tuning ability can combine analog computing and data storage at the device level. A major bottleneck for large-scale neuromorphic systems lies in the reliability issues of the analog RSM such as endurance and retention degradation and read/write noises and disturbances. Zhao and his team review these challenges and opportunities.3 

Analog hardware accelerators have the potential to overcome the major bottlenecks faced by digital hardware for data-heavy workloads such as deep learning. Exploiting this has proven to be challenging principally due to the overhead imposed by the peripheral circuitry and the nonideal properties of memory devices that play the role of the synapse. Xiao and his team explore a variety of approaches to overcome these challenges.4 

The elementary basis of intelligence in organisms with a central nervous system includes neurons and synapses and their complex interconnections forming neural circuits. In non-neural organisms such as slime mold with gel-like media, viscosity modulation enables adaptation to changing environments. Learning and memory are, therefore, multi-scale features that evolve because of constant interactions with the environment. In a brief review, Zhang and his team present a class of semiconductors called correlated oxides as candidates for learning machines.5 

Zhu and his team offer a comprehensive review on emerging artificial neuromorphic devices and their applications.6 They classify the devices into nine major categories and discuss their respective strengths and weaknesses. Zhang and his team review the mechanisms of various memristive devices that can mimic synaptic and neuronal functionalities, survey the progress of memristive spiking and artificial neural networks (ANNs), and compare different architectures.7 

Organic memories over the recent decades have promised a lot but delivered little. In their review, Goswami and his team analyze the root cause of the prolonged failures of organic memory devices and discuss a new family of organic memristors, made of transition metal complexes of redox active organic ligands (RALs), that satisfy and go beyond the requirements specified in the 2015 ITRS roadmap for RRAM devices.8 

In recent years, the emerging ferroic (ferroelectric and ferromagnetic) tunnel junctions have been shown to be able to function as memristors, which are potential candidates to emulate artificial synapses for neuromorphic computing. Here, Guo and his team provide a review on the ferroic tunnel junctions and their applications as artificial synapses in neuromorphic networks.9 

Functional emulation of biological synapses using electronic devices is regarded as the first step toward neuromorphic engineering and artificial neural networks (ANNs). Ling and his team review how electrolyte gating offers significant advantages for the realization of neuromorphic devices/architectures, including ultralow-voltage operation and the ability to form parallel-interconnected networks with minimal hardwired connectivity.10 

Coupled oscillators are highly complex dynamical systems, and it is an intriguing concept to use this oscillator dynamics for computation, motivated by biological observations: neural systems and mammalian brains, which seem to operate on oscillatory signals. Csaba and Porod review the various possibilities with this system.11 

The tensor core unit has been shown to outperform graphic processing units by almost three orders of magnitude, enabled by a stronger signal and greater energy efficiency. In this context, photons bear several synergistic physical properties, while phase-change materials allow for local nonvolatile mnemonic functionality in these emerging distributed non-von Neumann architectures. Miscuglio and Sorger review the challenges in implementing a photonic tensor core to perform tensor operations.12 

We strongly feel that with brain-like electronics we are at the cusp of an explosively growth opportunity for researchers,13 encompassing a wide array of capabilities ranging from materials science to data analytics.

1.
J. D.
Kendall
and
S.
Kumar
, “
The building blocks of a brain-inspired computer
,”
Appl. Phys. Rev.
7
,
011305
(
2020
).
2.
I.
Chakraborty
,
A.
Jaiswal
,
A. K.
Saha
,
S. K.
Gupta
, and
K.
Roy
, “
Pathways to efficient neuromorphic computing with non-volatile memory technologies
,”
Appl. Phys. Rev.
7
,
021308
(
2020
).
3.
M.
Zhao
,
B.
Gao
,
J.
Tang
,
H.
Qian
, and
H.
Wu
, “
Reliability of analog resistive switching memory for neuromorphic computing
,”
Appl. Phys. Rev.
7
,
011301
(
2020
).
4.
T. P.
Xiao
,
C. H.
Bennett
,
B.
Feinberg
,
S.
Agarwal
, and
M. J.
Marinella
, “
Analog architectures for neural network acceleration based on non-volatile memory
,”
Appl. Phys. Rev.
7
,
031301
(
2020
).
5.
H.-T.
Zhang
,
P.
Panda
,
J.
Lin
,
Y.
Kalcheim
,
K.
Wang
,
J. W.
Freeland
,
D. D.
Fong
,
S.
Priya
,
I. K.
Schuller
,
S. K. R. S.
Sankaranarayanan
,
K.
Roy
, and
S.
Ramanathan
, “
Organismic materials for beyond von Neumann machines
,”
Appl. Phys. Rev.
7
,
011309
(
2020
).
6.
J.
Zhu
,
T.
Zhang
,
Y.
Yang
, and
R.
Huang
, “
A comprehensive review on emerging artificial neuromorphic devices
,”
Appl. Phys. Rev.
7
,
011312
(
2020
).
7.
Y.
Zhang
,
Z.
Wang
,
J.
Zhu
,
Y.
Yang
,
M.
Rao
,
W.
Song
,
Y.
Zhuo
,
X.
Zhang
,
M.
Cui
,
L.
Shen
,
R.
Huang
, and
J. J.
Yang
, “
Brain-inspired computing with memristors: Challenges in devices, circuits, and systems
,”
Appl. Phys. Rev.
7
,
011308
(
2020
).
8.
S.
Goswami
,
S.
Goswami
, and
T.
Venkatesan
, “
An organic approach to low energy memory and brain inspired electronics
,”
Appl. Phys. Rev.
7
,
021303
(
2020
).
9.
R.
Guo
,
W.
Lin
,
X.
Yan
,
T.
Venkatesan
, and
J.
Chen
, “
Ferroic tunnel junctions and their application in neuromorphic networks
,”
Appl. Phys. Rev.
7
,
011304
(
2020
).
10.
H.
Ling
,
D. A.
Koutsouras
,
S.
Kazemzadeh
,
Y.
van de Burgt
,
F.
Yan
, and
P.
Gkoupidenis
, “
Electrolyte-gated transistors for synaptic electronics, neuromorphic computing, and adaptable biointerfacing
,”
Appl. Phys. Rev.
7
,
011307
(
2020
).
11.
G.
Csaba
and
W.
Porod
, “
Coupled oscillators for computing: A review and perspective
,”
Appl. Phys. Rev.
7
,
011302
(
2020
).
12.
M.
Miscuglio
and
V. J.
Sorger
, “
Photonic tensor cores for machine learning
,”
Appl. Phys. Rev.
7
,
031404
(
2020
).
13.
S.
Goswami
,
R.
Pramanick
,
A.
Patra
,
S.
Prasad Rath
,
M.
Foltin
,
A.
Ariando
,
D.
Thomson
,
T.
Venkatesan
,
S.
Goswami
, and
R. S.
Williams
, “
Decision trees within a molecular memristor
,”
Nature
597
,
51
56
(
2021
).