NEURAL NETWORK PARAMETER DEPLOYMENT METHOD, AI INTEGRATED CHIP, AND RELATED APPARATUS THEREOF

Embodiments of the present application relate to the field of terminals and provide an AI computing apparatus. The AI computing apparatus comprises an AI integrated chip and an off-chip memory. The AI integrated chip comprises a CPU, an NPU, a first on-chip memory unit and a second on-chip memory unit. The second on-chip memory unit is provided with a permission to only allow the NPU to read and a permission to only allow the CPU to write. The off-chip memory stores a first neural network code and a first weight parameter associated with the NPU, and the second on-chip memory unit stores a second neural network code and a second weight parameter associated with the NPU. The embodiments of the present application further provide an AI integrated chip, a neural network parameter deployment method, an electronic device, and a computer-readable storage medium. In the present application, the second neural network code and the second weight parameter which are relatively important are stored in the AI chip, the se