MIT’s AI can train neural networks faster than ever before
Abstract network molecular block chain structure - 3d rendered image on black background
Today, AI can design machine learning systems known as neural networks in a process called neural architecture search (NAS). But this technique requires a considerable amount of resources like time, processing power and money. Even for Google, producing a single convolution neural network -- often used for image classification -- takes 48,000 GPU hours. Now, MIT researchers have developed a NAS algorithm that automatically learns a convolution neural network in a fraction of the time -- just 200 GPU hours.
While this is certainly not uncomplicated, it could be a step toward putting AI and machine learning in the hands of more people and companies, freeing it from the towers of tech giants.
See the full story here: https://www.engadget.com/2019/03/22/mit-ai-automated-neural-network-design/