One Network to Fit All Hardware: New MIT AutoML Method Trains 14X Faster Than SOTA NAS | Synced

A group of MIT researchers (Han Cai, Chuang Gan and Song Han) have introduced a “Once for All” (OFA) network that achieves the same or better level accuracy as state-of-the-art AutoML methods on Im...

By · · 1 min read

Source: Synced | AI Technology & Industry Review

A group of MIT researchers (Han Cai, Chuang Gan and Song Han) have introduced a “Once for All” (OFA) network that achieves the same or better level accuracy as state-of-the-art AutoML methods on ImageNet, with a significant speedup in training time.