Lifeboat Foundation

Using machine learning three groups, including researchers at IBM and DeepMind, have simulated atoms and small molecules more accurately than existing quantum chemistry methods. In separate papers on the arXiv preprint server the teams each use neural networks to represent wave functions of electrons that surround the molecules’ atoms. This wave function is the mathematical solution of the Schrödinger equation, which describes the probabilities of where electrons can be found around molecules. It offers the tantalising hope of ‘solving chemistry’ altogether, simulating reactions with complete accuracy. Normally that goal would require impractically large amounts of computing power. The new studies now offer a compromise of relatively high accuracy at a reasonable amount of processing power.

Each group only simulates simple systems, with ethene among the most complex, and they all emphasise that the approaches are at their very earliest stages. ‘If we’re able to understand how materials work at the most fundamental, atomic level, we could better design everything from photovoltaics to drug molecules,’ says James Spencer from DeepMind in London, UK. ‘While this work doesn’t achieve that quite yet, we think it’s a step in that direction.’

Two approaches appeared on arXiv just a few days apart in September 2019, both combining deep machine learning and Quantum Monte Carlo (QMC) methods. Researchers at DeepMind, part of the Alphabet group of companies that owns Google, and Imperial College London call theirs Fermi Net. They posted an updated preprint paper describing it in early March 2020.¹ Frank Noé’s team at the Free University of Berlin, Germany, calls its approach, which directly incorporates physical knowledge about wave functions, PauliNet.²

An artificial neural network can reveal patterns in huge amounts of gene expression data, and discover groups of disease-related genes. This has been shown by a new study led by researchers at Linköping University, published in Nature Communications. The scientists hope that the method can eventually be applied within precision medicine and individualised treatment.

It’s common when using social media that the platform suggests people whom you may want to add as friends. The suggestion is based on you and the other person having common contacts, which indicates that you may know each other. In a similar manner, scientists are creating maps of biological networks based on how different proteins or genes interact with each other. The researchers behind a new study have used artificial intelligence, AI, to investigate whether it is possible to discover biological networks using deep learning, in which entities known as “artificial neural networks” are trained by experimental data. Since artificial neural networks are excellent at learning how to find patterns in enormous amounts of complex data, they are used in applications such as image recognition. However, this machine learning method has until now seldom been used in biological research.

“We have for the first time used deep learning to find disease-related genes. This is a very powerful method in the analysis of huge amounts of biological information, or ‘big data’,” says Sanjiv Dwivedi, postdoc in the Department of Physics, Chemistry and Biology (IFM) at Linköping University.

MANILA, Philippines — A dengue case forecasting system using space data made by Philippine developers won the 2019 National Aeronautics and Space Administration’s International Space Apps Challenge. Over 29,000 participating globally in 71 countries, this solution made it as one of the six winners in the best use of data, the solution that best makes space data accessible, or leverages it to a unique application.

Dengue fever is a viral, infectious tropical disease spread primarily by Aedes aegypti female mosquitoes. With 271,480 cases resulting in 1,107 deaths reported from January 1 to August 31, 2019 by the World Health Organization, Dominic Vincent D. Ligot, Mark Toledo, Frances Claire Tayco, and Jansen Dumaliang Lopez from CirroLytix developed a forecasting model of dengue cases using climate and digital data, and pinpointing possible hotspots from satellite data.

Correlating information from Sentinel-2 Copernicus and Landsat 8 satellites, climate data from the Philippine Atmospheric, Geophysical and Astronomical Services Administration of the Department of Science and Technology (DOST-PAGASA) and trends from Google search engines, potential dengue hotspots will be shown in a web interface.

Using satellite spectral bands like green, red, and near-infrared (NIR), indices like Fraction of Absorbed Photosynthetically Active Radiation (FAPAR) and Normalized Difference Vegetation Index (NDVI) are calculated in identifying areas with green vegetation while Normalized Difference Water Index (NDWI) identifies areas with water. Combining these indices reveal potential areas of stagnant water capable of being breeding grounds for mosquitoes, extracted as coordinates through a free and open-source cross-platform desktop geographic information system QGIS.

Check out the website here: http://aedesproject.org/

Here, in this article, I will try to give you an idea of how a genetic algorithm works and we will implement the genetic algorithm for function optimization. So, let’s start.

Last March, Chinese researchers announced an ingenious and potentially devastating attack against one of America’s most prized technological assets—a Tesla electric car.

The team, from the security lab of the Chinese tech giant Tencent, demonstrated several ways to fool the AI algorithms on Tesla’s car. By subtly altering the data fed to the car’s sensors, the researchers were able to bamboozle and bewilder the artificial intelligence that runs the vehicle.

Researchers from Carnegie Mellon and the University of Pittsburgh today published research showing how they’d solved a frustrating problem for people who use a brain-computer interface (BCI) to control prosthetic devices with their thoughts.

While the research itself is interesting – they created an algorithm that keeps the devices from constantly needing to be re-calibrated to handle the human brain’s fluctuating neuronal activity – the real takeaway here is how close we are to a universal BCI.

BCIs have been around for decades in one form or another, but they’re costly to maintain and difficult to keep working properly. Currently they only make sense for narrow use – specifically, in the case of those who’ve lost limbs. Because they’re already used to using their brain to control an appendage, it’s easier for scientists and researchers to harness those brainwaves to control prosthetic devices.

The research team, which also included Rodriguez’w PhD students Zou Geng and Kevin Peters, increased and decreased the distances between the mirrors at different speeds and noted how light transmitted through the cavity was affected. They saw that the direction in which the mirrors moved influenced how much light got through the cavity, finding that “the transmission of light through the cavity is non-linear.” This behavior of light, called hysteresis, is present in the phase transitions of boiling water or magnetic materials.

The scientists also increased the speed with which the oil-filled cavity opened and closed, observing that under such conditions the hysteresis was not always present. This allowed them to extrapolate a universal law. “The equations that describe how light behaves in our oil-filled cavity are similar to those describing collections of atoms, superconductors and even high energy physics,” elaborated Rodriguez, adding: “Therefore, the universal behavior we discovered is likely to be observed in such systems as well.”

For the last couple of years, Artificial Intelligence (AI) has been changing many fields and increasing efficiency by using improved datasets. One of those areas where AI has accelerated evolution is the robo-advisory, which is a field having extensive financial big data to analyze.

Robo-advisors are the systems that use algorithms to automatically perform investment decisions or tasks which are mostly done by human advisors. “Robo advisors are a potential solution to the complexities of financial decision making,” said Jill E. Fisch, a law professor at the University of Pennsylvania at a conference of Pension Research Council.

In the main scheme, robo-advisors are merging customers’ information such as their financial goals, risk tolerances, timeframes, with the right asset allocation that qualifies customer’s needs. While making this merge, they use many algorithms including machine learning models to create the best fit for the customer. In the process of timeframe, they take lots of actions as well such as rebalancing the portfolio or performing tax-loss harvesting. This automatically increases efficiency while taking decisions at the right time for the portfolio.

Researchers have discovered a new Earth-sized planet orbiting a star outside our solar system. The planet, called Kepler-1649c, is only around 1.06 times larger than Earth, making it very similar to our own planet in terms of physical dimensions. It’s also quite close to its star, orbiting at a distance that means it gets around 75% of the light we do from the Sun.

The planet’s star is a red dwarf, which is more prone to the kind of flares that might make it difficult for life to have evolved on its rocky satellite’s surface, unlike here in our own neighborhood. It orbits so closely to its star, too, that one year is just 19.5 of our days — but the star puts out significantly less heat than the Sun, so that’s actually right in the proper region to allow for the presence of liquid water.

Kepler-1649c was found by scientists digging into existing observations gathered by the Kepler space telescope before its retirement from operational status in 2018. An algorithm that was developed to go through the troves of data collected by the telescope and identify potential planets for further study failed to properly ID this one, but researchers noticed it when reviewing the information.