Toggle light / dark theme

Researchers at the Research Center for IT Innovation of Academia Sinica, in Taiwan, have recently developed a novel generative adversarial network (GAN) that has binary neurons at the output layer of the generator. This model, presented in a paper pre-published on arXiv, can directly generate binary-valued predictions at test time.

So far, GAN approaches have achieved remarkable results in modeling continuous distributions. Nonetheless, applying GANs to discrete data has been somewhat challenging so far, particularly due to difficulties in optimizing the distribution toward the target data distribution in a high-dimensional discrete space.

Hao-Wen Dong, one of the researchers who carried out the study, told Tech Xplore, “I am currently working on music generation in the Music and AI Lab at Academia Sinica. In my opinion, composing can be interpreted as a series of decisions—for instance, regarding the instrumentation, chords and even the exact notes to use. To move toward achieving the grand vision of a solid AI composer, I am particularly interested in whether deep generative models such as GANs are able to make decisions. Therefore, this work examined whether we can train a GAN that uses binary neurons to make binary decisions using backpropagation, the standard training algorithm.”

Read more

The German space agency DLR carried out the tests in January last year on the MAIUS 1 rocket, beating NASA’s Cold Atom Laboratory who have also since produced a BEC in space.

The findings have been published this week in the journal Nature.

Scientists at 11 German research facilities miniaturised the technology for the production of Bose-Einstein condensates which normally fills a whole lab room.

Read more

According to Einstein’s General Relativity, gravity travels at the speed of light. Proving it is far from simple, though: unlike light, gravity can’t simply be switched on and off, and is also extremely weak.

Over the years, various attempts have been made to measure the speed using studies of astronomical phenomena, such as the time delay of light as it passes through the huge gravitational field of Jupiter. While the results have been broadly in line with Einstein’s prediction, they’ve lacked the precision needed for compelling evidence. That’s now been provided by the celebrated detection of gravitational waves. Analysis of the signals picked up by the two giant LIGO instruments in the US has confirmed that gravity does indeed travel through space at the speed of light.

Read more