Neuromorphic circuits emulating the bio‐brain functionality via artificial devices have achieved a substantial scientific leap in the past decade. However, even with the advent of highly advanced bio‐inspired algorithms, the artificial intelligence based on current neuromorphic circuits is lagging behind significantly when compared with naturally evolved biological neural circuits. This massive and intriguing discrepancy is partly due to the incomprehensive understanding of bio‐brain operating mechanism, which relies heavily on the extremely complexed entangled 3D hierarchical neural networks. Configuring 3D neuromorphic hardware with combined computing and memory functionalities, coupled with compatible progress of software algorithms, can be an inevitable route to surmount the limitation encountered by current 2D artificial circuits. Herein, referring to the neuron configuration in 3D perspective together with detailed signal generation and propagation mechanism, the von Neumann configuration is compared with state‐of‐the‐art in‐memory computing architecture, and the development and perspectives of 3D in‐memory computing neuromorphic circuits are highlighted.

Bio‐Inspired 3D Artificial Neuromorphic Circuits

Linear Classification Function Emulated by Pectin-Based Polysaccharide-Gated Multiterminal Neuron Transistors

Artificial neurons have received extensive attention as an important part of neuromorphic computing. Recently, tremendous efforts have been made on the memristor-based neurons, while the regulation of performance of such neurons and its underlining mechanism has been rarely studied. In this work, we propose an artificial neuron device based on Ag/TaOx/Si, which exhibits good threshold switching characteristics (on-off ratio above 105) along with good device stability and cycling stability. The Leaky Integrate-and-Fire (LIF) neuron model is successfully simulated without additional circuitry, including leaky integrated firing and refractory periods. In addition, the effect of oxygen vacancy concentration on the performance of artificial neurons is investigated, and the results showed that an increase of oxygen vacancies can significantly reduce the threshold voltage of neuron activation, the holding voltage and the probability of refractory period. This work provides a simple and effective strategy for the development of artificial neurons with tunable properties.

A Memristor-Based Leaky Integrate-and-Fire Artificial Neuron With Tunable Performance

Temperature has always been considered as an essential factor for almost all kinds of semiconductor-based electronic components. In this work, temperature-dependent synaptic plasticity behaviors, which are mimicked by the indium–gallium–zinc oxide thin-film transistors gated with sputtered SiO2 electrolytes, have been studied. With the temperature increasing from 303 to 323 K, the electrolyte capacitance decreases from 0.42 to 0.11 μF cm–2. The mobility increases from 1.4 to 3.7 cm2 V–1 s–1, and the threshold voltage negatively shifts from −0.23 to −0.51 V. Synaptic behaviors under both a single pulse and multiple pulses are employed to study the temperature dependence. With the temperature increasing from 303 to 323 K, the post-synaptic current (PSC) at the resting state increases from 1.8 to 7.3 μA. Under a single gate pulse of 1 V and 1 s, the PSC signal altitude and the PSC retention time decrease from 2.0 to 0.7 μA and 5.1 × 102 to 2.5 ms, respectively. A physical model based on the electric field-induced ion drifting, ionic–electronic coupling, and gradient-coordinated ion diffusion is proposed to understand these temperature-dependent synaptic behaviors. Based on the experimental data on individual transistors, temperature-modulated pattern learning and memorizing behaviors are conceptually demonstrated. The in-depth investigation of the temperature dependence helps pave the way for further electrolyte-gated transistor-based neuromorphic applications.

Sputtered Electrolyte-Gated Transistor with Temperature-Modulated Synaptic Plasticity Behaviors

Recently, artificial neurons have attracted much attention due to their excellent energy efficiency and scalability. However, there are still few reports on the regulation of the performance of artificial neuron based on single device. In the letter, we present an artificial neuron device based on Ag/TaOx/Si that not only has excellent turn-on and turn-off performance, but also exhibits sustained stability under multiple cycle tests. Moreover, the Integrate -and-Fire (IF) neuron model is successfully simulated at room temperature. More importantly, we find that an increase of temperature could reduce the threshold voltage and reset voltage of neurons, improve the probability of neuronal firing, and promote the transformation of neurons from nonvolatile to volatile. This work provides an effective method for regulating artificial neurons and has important implications for studying information transfer in biology and adapting complex computations in a memory computing framework.

Temperature Regulated Artificial Neuron Based on Memristor

A new trend in brain-like computing is to develop more biologically realistic neurons in order to accurately replicate the computational power of the biological counterparts. The brain-like computing platforms based on these models that resemble the organization of neurons in brain would serve as a more efficient tool than traditional hardware. Recently, with the rapid development of neuromorphic devices, the realization of biologically-accurate neurons to fit these models becomes feasible. In view of this, we summarize the most recent progress on neuromorphic devices for achieving the essential neuronal information processing functions of a biological neuron. Despite its infancy, the biologically-accurate neuron already has exhibited an unprecedented potential to boost the hardware implementation of brain-like computation as well as leading a trend on neurorobotics and prosthetics. Challenges and perspectives are also addressed to shed light on future advances with respect to practical applications and t...

Jiaofu Li

Papers

The Emerging Devices for Biologically-Accurate Neuron