It’s All Pattern Catching
Many believe that true quantum computing will enable computations that supercomputers would take hundreds of years to process, enabling real-time weather prediction, custom drug design and cracking encryption. Geordie Rose isn’t promising those kinds of universal applications, at least not immediately.
“The breadth of applications is actually quite narrow. The machine can be thought of most profitably as an analogue computer. It’s not exactly an analogue computer, it’s something novel that has never existed before but conceptually you can think of it as a special purpose chip designed to do one thing well. Ultimately, quantum computers will turn into a lot more than that but when you do the first iteration of a technology, it helps to focus what it does. This particular chip, all it does is problems related to pattern matching. Other applications such as code breaking; this chip is disabled in a way that makes those things not possible to run on it. It is possible that in future we might expand - if this particular project succeeds financially – to include other type of processors that are able to harness nature in way that allows you to do these things. But those are long term things and certainly not our focus right now.”
At the Future in Review conference this year Rose showed an image matching program developed with Google image matching expert, Dr Hartmut Neven, that can distinguish photos of, say, the Taj Mahal from photos of Big Ben by comparing the image to a group of images already labelled as the Taj Mahal. The software looks for matching points of interest in the photos, which means solving hard maths problems that Orion is very good at, according to Rose. “Similarity matching between images is a very hard artificial intelligence problem and it turns out, with quantum computers, that their sweet spot is in the technical math that underlies certain hard vision problems and certain hard machine learning problems.”
You can match images and look for patterns on conventional computers, but it takes a lot of time it train the system, says Rose. “The requirement to do very fast search on a large number of images requires that you sacrifice quality. Often what happens in image search is that you can do very well on finding certain types of objects in images by spending a lot of time up front. You can detect faces in photos very quickly if you spend a year using an enormous amount of computing cycles to do that.”
Using Orion won’t necessarily speed up the time it takes to search, but he believes it will produce much better matches to what you’re looking for, and he’s not worried by performance that’s actually slower than conventional computing today. “This is not a demonstration of performance; this is a demonstration that we can do this end to end. We will be able to get a quality of matching on large data sets you simply can’t get with conventional computing, no matter how good your algorithms are. When you are searching for something complicated or unique it’s sometimes hard to describe. This is the first step of a system where you can query not with text but with images; it’s the sweet spot of the next generation of search and what these computers do very well.”
Pattern matching covers a wide range of applications. D-wave has previously demonstrated searching a database of molecules, creating a seating plan with many constraints on who can sit together and solving Sudoku puzzles and commercial applications are the next step. Rose talks about improving the logistics of how jet fuel is distributed and stored, cataloguing stars in images of space, modelling protein folding and counting the number of rocks in a possible landing area on Mars but also solving complex business problems: “What is the ideal business unit in my company to work on this project? I need three people who know C++ and earn less than such and such...”
But Orion isn’t anywhere near ready to go in your data center. It’s going to be staying in D-wave’s headquarters in Burnaby, Canada for the immediate future, because of what Rose calls the “extraordinary” cooling requirements. The Josephson junctions are only microns across; the chip they’re on is 5 millimetres square. But Orion itself is roughly the size of a large domestic refrigerator, and most of the system is taken up by the refrigeration equipment.
“This thing sits inside a shielded room, a big metal room which is almost a magnetic vacuum for certain frequencies of EM radiation. Inside is an insert which is half fridge and half filtering. We run this thing at ten milliKelvin, just 0.01 degrees above absolute zero – and just for a point of reference the temperature of interstellar space is about 2.7 Kelvin. The chip needs to sit in a magnetic vacuum. A lot of the gadgetry inside this is very, very robust filters that filter out every bit of noise you can with current technology, to get the signals on the lines coming in and the ambient magnetic field to very low levels - one nanotesla in three dimensions across the whole chip, which is at or beyond the state of the art for magnetic vacuum technology.”
