challenges in terms of speed and power usage, while neural algorithms show the potential to bypass the Von Neumann bottleneck and exceed Moore's Limitation. [1] Compared to traditional computers, the biological brain excels in learning, generalization, abstraction, and applicability. [2] Scientists have created a range of synaptic devices inspired by the structure and function of the human brain, using physical processes, and functional materials. [3] Due to their cost-effectiveness, scalability, integrated density, and low power consumption, emerging two-terminal meristem devices are potential possibilities. [4] However, low on/off current ratios, nonlinear, and asymmetric conductance changes lead to low numbers of synaptic weight and inferior linearity of synaptic weight changes. [5] Furthermore, an additional selector component is needed to select the target cell. In comparison, threeterminal synaptic transistors can exhibit low read/write currents, parallel write and read operations, low power consumption, and quasi-linear weight change, which can improve the controllability of prominent weight thereby avoiding the crosstalk problems. [6] Moreover, the post-synaptic received signal cannot be easily disrupted by the pre-synaptic input signal in the three-terminal device, which is crucial to the design of multi-input devices. [7a] Three-terminal synaptic device can control synaptic weights more easily than two-terminal synaptic device because of its structural properties of independent terminals in both training and testing phases. The gate is used for training, and the source-drain and channel are used in the test phase. [5] This structural feature prevents synaptic weights from being destroyed during the testing phase. [7b] As a promising candidate for neuromorphic applications, three-terminal electrolyte-gated synaptic transistors (EGSTs) have drawn considerable attention owe to their low operation voltages, similarity to actual biological systems through the evolutionary structural design of synaptic transistor functions. [6a,b,8] The neural networks of the brain are built on the contributions of excitatory and inhibitory neurons. Presynaptic impulses can activate or inhibit post-synaptic neurons in signal processing, memory, and learning. [6e] Specifically, excitatory postsynaptic potentials cause postsynaptic neurons to produce action potentials. In contrast, inhibitory postsynaptic potentials counterbalance excitatory effects, making postsynaptic neurons less Artificial synapses have attracted extensive attention due to their capacity to circumvent the inherent restrictions of Von Neumann computing architecture. Although electrolyte-gated synaptic transistors (EGSTs) have been enabled to emulate the essential synaptic plasticity, the corresponding neurological applications have been restricted by the lack of inhibitory synaptic response and the subsequent low asymmetric non-linearity factor. Here, Mg-doped SnO 2 (Mg:SnO 2 ) EGSTs via a low-cost and facile solution method are fabricated. With ...