Edge AI: Addressing the Efficiency Paradigm
Colleen P. Bailey, Arthur C. Depoian, Ethan R. Adams · 2022
Recent years have seen a growing trend towards massive deep learning neural network algorithms. This movement is further perpetuated by the rapid growth in available computation. While these giant models attain remarkable performance, the required computational cost is proportionally huge. There is a resulting necessity for efficient and intelligent algorithm design that can achieve similar high performance to current state-of the-art.