MIT researchers have a new and better way to compress models.It's so simple that they unveiled it in a tweet last month: Train the model, prune its weakest connections, retrain the model at its fast, early training rate, and repeat, until the model is as tiny as you want.
"We study spiking neural networks, which are systems that learn much as living brains do," said Los Alamos National Laboratory computer scientist Yijing Watkins. "We were fascinated by the prospect of training a neuromorphic processor in a manner analogous to how humans and other biological systems learn from their environment during childhood development."Watkins and her research team found that the network simulations became unstable after continuous periods of unsupervised learning. When they exposed the networks to states that are analogous to the waves that living brains experience during sleep, stability was restored. "It was as though we were giving the neural networks the equivalent of a good night's rest," said Watkins.