In particular, artificial synapses are the core parts of neuromorphic systems because they perform information processing like pattern recognition, output prediction, and learning and store memory by regulating synaptic weight in response to presynaptic signals. [3] In these operations, the operation accuracy differs based on synaptic characteristics such as the symmetry and linearity of synaptic weight change, ratio of maximum to minimum conductance, and number of synaptic weights. [4,5] To accomplish high operation accuracy of neuromorphic systems, which are analogous to the human brain, variety sort of 2-terminal and 3-terminal devices as artificial synapsesThe ORCID identification number(s) for the author(s) of this article can be found under

2D semiconductor‐based ferroelectric field effect transistors (FeFETs) have been considered as a promising artificial synaptic device for implementation of neuromorphic computing systems. However, an inevitable problem, interface traps at the 2D semiconductor/ferroelectric oxide interface, suppresses ferroelectric characteristics, and causes a critical degradation on the performance of 2D‐based FeFETs. Here, hysteresis modulation method using self‐assembly monolayer (SAM) material for interface trap passivation on 2D‐based FeFET is presented. Through effectively passivation of interface traps by SAM layer, the hysteresis of the proposed device changes from interface traps‐dependent to polarization‐dependent direction. The reduction of interface trap density is clearly confirmed through the result of calculation using the subthreshold swing of the device. Furthermore, excellent optic‐neural synaptic characteristics are successfully implemeted, including linear and symmetric potentiation and depression, and multilevel conductance. This work identifies the potential of passivation effect for 2D‐based FeFETs to accelerate the development of neuromorphic computing systems.

With the significant technological developments in recent times, the neuromorphic system has been receiving considerable attention owing to its parallel arithmetic, low power consumption, and high scalability. However, the low reliability of artificial synapse devices disturbs calculations and causes inaccurate results in neuromorphic systems. In this paper, we propose a stable resistive artificial synapse (RAS) device with nitrogen-doped titanium oxide (TiO x :N)-based resistive switching (RS) memory. The TiO x :N-based RAS, compared to the TiO x -based RAS, demonstrates more stable RS characteristics in current–voltage (I–V) and pulse measurements. In terms of resistance variability, the TiO x :N-based RAS demonstrates five times lower resistance variability at 1.38%, compared to 6.68% with the TiO x -based RAS. In addition, we verified the relation between the neuromorphic system and the resistance reliability of the synapse device for the first time. The pattern recognition simulation is performed using an artificial neural network (ANN) consisting of artificial synapse devices using the Modified National Institute of Standards and Technology dataset. In the simulation, the ANN with the TiO x :N-based RAS exhibited significant pattern recognition accuracy of 64.41%, while the ANN with TiO x -based RAS demonstrated only low recognition accuracy of 22.07%. According to the results of subsequent simulations, the pattern recognition accuracy exponentially decreases when the resistance variability exceeds 5%. Therefore, for implementing a stable neuromorphic system, the synapse device in the neuromorphic system has to maintain low resistance variability. The proposed nitrogen-doped synapse device is suitable for neuromorphic systems because reliable resistance variability can be obtained with only simple process steps.

Neural networks composed of artificial neurons and synapses mimicking the human nervous system have received much attention because of their promising potential in future computing systems. In particular, spiking neural networks (SNNs), which are faster and more energy‐efficient than conventional artificial neural networks, have recently been the focus of attention. However, because typical neural devices for SNNs are based on complementary metal‐oxide‐semiconductors that exhibit high consumption of power and require a large area, it is difficult to use them to implement a large‐scale network. Thus, a new structure should be developed to overcome the typical problems that have been encountered and to emulate bio‐realistic functions. This study proposes a versatile artificial neuron based on the bipolar electrochemical metallization threshold switch, which exhibits four requisite characteristics for a spiking neuron: all‐or‐nothing spiking, threshold‐driven spiking, refractory period, and strength‐modulated frequency. Furthermore, unique features such as an inhibitory postsynaptic potential and the bipolar switching characteristic for changing synaptic weight are realized. Additionally, by using a filament confinement technique, a high on/off ratio (≈6 × 107), a low threshold voltage (0.19 V), low variability (0.014), and endurance over 106 cycles are achieved. This research will serve as a stepping‐stone for advanced large‐scale neuromorphic systems.

No abstract