Kicking neural network design automation into high gear

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. 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. Instead of discarding neurons, however, the researchers’ NAS algorithm prunes entire paths, which completely changes the neural network’s architecture.

Source: news.mit.edu