Restricted Boltzmann machines (RBMs) are powerful machine learning models, but learning and some kinds of inference in the model require sampling-based approximations, which, in classical digital computers, are implemented using expensive MCMC. Physical computation offers the opportunity to reduce the costof sampling by building physical systems whose natural dynamics correspond to drawing samples from the desired RBM distribution. Such a system avoids the burn-in and mixing cost of a Markov chain. However, hardware implementations of this variety usually entail limitations such as low-precision and limited range of the parameters and restrictions on the size and topology of the RBM. We conduct software simulations to determine how harmful each of these restrictions is. Our simulations are based on the D-Wave Two computer, but the issues we investigate arise in most forms of physical computation.Our findings suggest that designers of new physical computing hardware and algorithms for physical computers should focus their efforts on overcoming the limitations imposed by the topology restrictions of currently existing physical computers.
Computers have become much more adept at translating from one language into another in recent years, thanks to the application of neural networks. However, these AI systems usually require a lot of content translated by humans for the computers to learn from, while two new papers demonstrate that it's possible to develop a system that doesn't rely on parallel texts.
Anyone who's even remotely familiar with the world of information technology might have come across words like machine learning and artificial intelligence. Artificial intelligence has long been a part of pop culture. If tech bigwigs are to be believed, artificial intelligence and machine learning are the future of our world and technology. But what is machine learning? And how are machine learning and artificial intelligence connected?
A University of Arizona information scientist wants to make computers behave more like natural human partners. UA researcher Clay Morrison focuses on machine learning. He is looking at ways to get artificial intelligence to work alongside people. "We're not trying to say the computer has to behave exactly like a human," he said. "Instead it's how the computer is natural enough to interact with, so when we team up with them and they collaborate with us on a project, the strengths the computer brings to the table and the strengths the human brings to the table are really much more effectively combined."