What is neural architecture search (NAS) model compression?

NAS is a very broad field of research, so here people should just focus on its use for compressing pre-trained models, specifically. NAS in the most general sense is a search over a set of decisions that define the different components of a neural network—it is a systematic, automized way of learning optimal model architectures. The idea is to remove human bias from the process to arrive at novel architectures that perform better than human-designed ones.

Share it on social networks: Tweet Share