The development of computation technology and artificial intelligence (AI) field brings\nabout AI to be applied to various system. In addition, the research on hardware-based AI processors\nleads to the minimization of AI devices. By adapting the AI device to the edge of internet of things\n(IoT), the system can perform AI operation promptly on the edge and reduce the workload of the\nsystem core. As the edge is influenced by the characteristics of the embedded system, implementing\nhardware which operates with low power in restricted resources on a processor is necessary. In this\npaper, we propose the intellino, a processor for embedded artificial intelligence. Intellino ensures\nlow power operation based on optimized AI algorithms and reduces the workload of the system\ncore through the hardware implementation of a neural network. In addition, intellinoâ??s dedicated\nprotocol helps the embedded system to enhance the performance. We measure intellino performance,\nachieving over 95% accuracy, and verify our proposal with an field programmable gate array\n(FPGA) prototyping.
Loading....