Lifeboat Foundation

Creating images from text in seconds—and doing so with a conventional graphics card and without supercomputers? As fanciful as it may sound, this is made possible by the new Stable Diffusion AI model. The underlying algorithm was developed by the Machine Vision & Learning Group led by Prof. Björn Ommer (LMU Munich).

“Even for laypeople not blessed with artistic talent and without special computing know-how and computer hardware, the new model is an effective tool that enables computers to generate images on command. As such, the model removes a barrier to ordinary people expressing their creativity,” says Ommer. But there are benefits for seasoned artists as well, who can use Stable Diffusion to quickly convert new ideas into a variety of graphic drafts. The researchers are convinced that such AI-based tools will be able to expand the possibilities of creative image generation with paintbrush and Photoshop as fundamentally as computer-based word processing revolutionized writing with pens and typewriters.

In their project, the LMU scientists had the support of the start-up Stability. Ai, on whose servers the AI model was trained. “This additional computing power and the extra training examples turned our AI model into one of the most powerful image synthesis algorithms,” says the computer scientist.

Researchers have developed a machine learning algorithm that could help reduce charging times and prolong battery life in electric vehicles by predicting how different driving patterns affect battery performance, improving safety and reliability.

The researchers, from the University of Cambridge, say their algorithm could help drivers, manufacturers and businesses get the most out of the batteries that power electric vehicles by suggesting routes and driving patterns that minimize battery degradation and charging times.

The team developed a non-invasive way to probe batteries and get a holistic view of battery health. These results were then fed into a machine learning algorithm that can predict how different driving patterns will affect the future health of the battery.

In a study published in Cell Reports, we present a novel algorithm for the digital generation of neuronal morphologies, based on the topology of their branching structure. This algorithm generates neurons that are statistically similar to the biological neurons, in terms of morphological properties, electrical responses and the connectivity of the networks they form.

This study represents a major milestone for the Blue Brain Project and for the future of computational neuroscience. The topological neuron synthesis enables the generation of millions of unique neuronal shapes from different cell types. This process will allow us to reconstruct brain regions with detailed and unique neuronal morphologies at each cell position.

The topological representation of neurons facilitates the generation of neurons that approximate morphologies that are structurally altered compared to healthy neuronal morphologies. These structural alterations of neurons are disrupting the brain systems and are contributing factors to brain diseases. The topological synthesis can be used to study the differences between healthy and diseased states of different brain regions and specifically, what structural alterations of neurons are causing important problems to the networks they form.

A breakthrough low-memory technique by Rice University computer scientists could put one of the most resource-intensive forms of artificial intelligence—deep-learning recommendation models (DLRM)—within reach of small companies.

DLRM recommendation systems are a popular form of AI that learns to make suggestions users will find relevant. But with top-of-the-line training models requiring more than a hundred terabytes of memory and supercomputer-scale processing, they’ve only been available to a short list of technology giants with deep pockets.

Rice’s “random offset block embedding array,” or ROBE Array, could change that. It’s an algorithmic approach for slashing the size of DLRM memory structures called embedding tables, and it will be presented this week at the Conference on Machine Learning and Systems (MLSys 2022) in Santa Clara, California, where it earned Outstanding Paper honors.

Superfast algorithm put crimp in 2019 claim that Google’s machine had achieved “quantum supremacy”.

Turbulence plays a key role in our daily lives, making for bumpy plane rides, affecting weather and climate, limiting the fuel efficiency of the cars we drive, and impacting clean energy technologies. Yet, scientists and engineers have puzzled at ways to predict and alter turbulent fluid flows, and it has long remained one of the most challenging problems in science and engineering.

Now, physicists from the Georgia Institute of Technology have demonstrated—numerically and experimentally—that turbulence can be understood and quantified with the help of a relatively small set of special solutions to the governing equations of fluid dynamics that can be precomputed for a particular geometry, once and for all.

“For nearly a century, turbulence has been described statistically as a random process,” said Roman Grigoriev. “Our results provide the first experimental illustration that, on suitably short time scales, the dynamics of turbulence is deterministic—and connects it to the underlying deterministic governing equations.”

From my understanding, inertia is typically taken as an axiom rather than something that can be explained by some deeper phenomenon. However, it’s also my understanding that quantum mechanics must reduce to classical, Newtonian mechanics in the macroscopic limit.

By inertia, I mean the resistance to changes in velocity — the fact of more massive objects (or paticles, let’s say) accelerating more slowly given the same force.

What is the quantum mechanical mechanism that, in its limit, leads to Newtonian inertia? Is there some concept of axiomatic inertia that applies to the quantum mechanical equations and explains Newtonian inertia, even if it remains a fundamental assumption of quantum theory?

The tool can identify symptoms of dengue, malaria, leptospirosis, and scrub typhus.

The study investigates both statistical and machine learning approaches. WHO has categorized dengue as a “neglected tropical disease.”

A prediction tool based on multi-nominal regression analysis and a machine learning algorithm was developed.

Continue reading “AI could revolutionize healthcare but can we trust it?” »

Summary: A newly developed artificial intelligence model can detect Parkinson’s disease by reading a person’s breathing patterns. The algorithm can also discern the severity of Parkinson’s disease and track progression over time.

Source: MIT

Parkinson’s disease is notoriously difficult to diagnose as it relies primarily on the appearance of motor symptoms such as tremors, stiffness, and slowness, but these symptoms often appear several years after the disease onset.