Artificial synapses combined with artificial neural networks can develop next-generation computer framework. This computer framework has the characteristics of low energy consumption, high density, self-learning and self-storage. We designed and prepared artificial synapse based on all-inorganic perovskite Cs2AgBiBr6 (CABB). This work studies the synaptic excitatory behavior of CABB synapses in neurology. By applying electrical spikes, it can exhibit excitatory behaviors similar to biological synapses. On this basis, using its synaptic excitement, we simulated some conceived functions of human-like artificial intelligence, including pain simulation, Pavlov learning, letter learning and number recognition. After testing, it can be found that CABB synapse can complete these tasks. In order to realize number recognition, we designed a multi-layer neural network according to the weight update method of CABB synapse. It shows a recognition accuracy of 91.57 %.