“Training Imagenet in 3 Hours for $25; and CIFAR-10 for $0.26”, Jeremy Howard2018-04-30 (, ; backlinks; similar)⁠:

…Their goal was simply to deliver the fastest image classifier as well as the cheapest one to achieve a certain accuracy (93% for Imagenet, 94% for CIFAR-10). In the CIFAR-10 competition our entries won both training sections: fastest, and cheapest…In the Imagenet competition, our results were:

Using:

…I worry when I talk to my friends at Google, OpenAI, and other well-funded institutions that their easy access to massive resources is stifling their creativity. Why do things smart when you can just throw more resources at them? But the world is a resource-constrained place, and ignoring that fact means that you will fail to build things that really help society more widely. It is hardly a new observation to point out that throughout history, constraints have been drivers of innovation and creativity. But it’s a lesson that few researchers today seem to appreciate.

Please read “Now anyone can train Imagenet in 18 minutes” for further breakthroughs. [See also “Measuring the Algorithmic Efficiency of Neural Networks”, Hernandez & Brown2020 for estimates of overall improvements in compute/cost-efficiency of Imagenet training historically as it follows an experience curve.]