Once the first model checkpoint is created, you can start sampling. The latest model checkpoint will be retrieved and used to sample. We can however trade computation cost with accuracy and fidility by lowering the sampling rate, amount of stacks and the amount of channels per layer. For a downsized model (4000hz vs 16000 sampling rate, 16 filters v/s 256, 2 stacks vs??

Now, researchers from Google DeepMind and Stanford University have updated a theory originally developed to explain how humans and other animals learn. "The evidence seems compelling that the brain has these two kinds of learning systems, and the complementary learning systems theory explains how they complement each other to provide a powerful solution to a key learning problem that faces the brain," explained James McClelland, lead author of the 1995 paper from Stanford University. Components of the neural network architecture that succeeded in achieving human-level performance in a variety of computer games like Space Invaders and Breakout were inspired by complementary learning systems theory. According to DeepMind co-founder Demis Hassabis, "the extended version of the complementary learning systems theory is likely to continue to provide a framework for future research not only in neuroscience but also in the quest to develop Artificial General Intelligence -- our goal at Google DeepMind."

He continued: "We wanted to see if we could build a system that could learn to play and beat the best Go players by just providing the games of professional players. We are thrilled to have achieved this milestone, which has been a lifelong dream of mine. Our hope is that in the future we can apply these techniques to other challenges -- from instant translation to smartphone assistants to advances in health care."