Kicking neural network automation into high gear

ScienceDaily | 3/21/2019 | Staff
Click For Photo: https://www.sciencedaily.com/images/2019/03/190321152843_1_540x360.jpg

One of the state-of-the-art NAS algorithms recently developed by Google took 48,000 hours of work by a squad of graphical processing units (GPUs) to produce a single convolutional neural network, used for image classification and identification tasks. Google has the wherewithal to run hundreds of GPUs and other specialized circuits in parallel, but that's out of reach for many others.

In a paper being presented at the International Conference on Learning Representations in May, MIT researchers describe an NAS algorithm that can directly learn specialized convolutional neural networks (CNNs) for target hardware platforms -- when run on a massive image dataset -- in only 200 GPU hours, which could enable far broader use of these types of algorithms.

Researchers - Companies - Algorithm - Researchers - Goal

Resource-strapped researchers and companies could benefit from the time- and cost-saving algorithm, the researchers say. The broad goal is "to democratize AI," says co-author Song Han, an assistant professor of electrical engineering and computer science and a researcher in the Microsystems Technology Laboratories at MIT. "We want to enable both AI experts and nonexperts to efficiently design neural network architectures with a push-button solution that runs fast on a specific hardware."

Han adds that such NAS algorithms will never replace human engineers. "The aim is to offload the repetitive and tedious work that comes with designing and refining neural network architectures," says Han, who is joined on the paper by two researchers in his group, Han Cai and Ligeng Zhu.

Work - Researchers - Ways - Network - Design

In their work, the researchers developed ways to delete unnecessary neural network design components, to cut computing times and use only a fraction of hardware memory to run a NAS algorithm. An additional innovation ensures each outputted CNN runs more efficiently on specific hardware platforms -- CPUs, GPUs, and mobile devices -- than those designed by traditional approaches. In tests, the researchers' CNNs were 1.8 times...
(Excerpt) Read more at: ScienceDaily
Wake Up To Breaking News!
Sign In or Register to comment.

Welcome to Long Room!

Where The World Finds Its News!