In this magical world of technology, if there is one term that has taken everyone by storm, then it has to be – Artificial Intelligence, without a doubt. Over the years, Artificial Intelligence, or AI as it is commonly called, has seen varied applications in every field possible – be it healthcare, e-commerce, robotics and even banking for that matter. However, that one field that is relatively less explored but is as interesting and exciting as the rest is astronomy.

Talking about astronomy, one of the toughest challenges lies in studying the data. It is because of this that astronomers are turning towards machine learning and Artificial Intelligence (AI) in order to build new tools. Having said that, have a look at how has Artificial Intelligence transformed astronomy and is catering to the needs of astronomers.

• Off late, a group of astronomers made use of Artificial Intelligence in a galaxy merger study to confirm that the driving force behind starbursts was nothing but galaxy mergers. Considering how large the database turned out to be, the team had built a deep learning algorithm that taught itself to identify merging galaxies. One of the astronomers was quoted as saying that the advantage of Artificial Intelligence is that it would improve the reproducibility of the study. The reason being – the algorithm is consistent in its definitions of a merger.

• One of the most crucial tasks to accomplish for an astronomer is to hunt a p The whole science behind this is – Whenever there is an exoplanet passing in front of its parent star, some of the light is blocked, which the humans can see. It is here that the astronomers observe the orbits of an exoplanet and build a picture of the dips in the light. After doing so, they identify various properties of the planet such as its mass, size and distance from its star to name a few. That said, AI turns out to be no less than a saviour here. By virtue of AI’s time-series analysis techniques, it is possible to analyse data as a sequential sequence and thus identify the signals of exoplanets with as much as up to 96 percent accuracy.

• The changing sky – The changing sky has grabbed all the attention for it has made its way to become one of the most remarkable projects of all time. This aims to survey the entire night sky every night – collecting over 80 terabytes of images in one go to be able to learn how the stars and galaxies in the universe vary with time.

• Gravitational waves – Finding the signals of the most catastrophic events in the universe is very important for astronomers. What happens here is – when exoplanets fall inwards, they send out ripples in space-time. These can further be detected by measuring faint signals here on Earth. Gravitational-wave detector collaborations – Ligo and Virgo have worked exceptionally well in this aspect. Both of them have been successful in identifying signals with the help of machine learning. The astronomers now get alerts as a result of which they can turn their telescopes in the right direction.

The post HOW HAS ARTIFICIAL INTELLIGENCE TRANSFORMED ASTRONOMY? appeared first on Artificial Intelligence.

The goal of quantum chemistry is to predict chemical and physical molecular properties based on the position of their atoms in space and avoiding laboratory experiments that require significant resources and time. Generally, this can be achieved by solving the Schrodinger equation, however, in practice, this is hard to achieve.

Recently, artificial intelligence (AI) has been used to solve the Schrodinger Equation in quantum chemistry. A team of scientists at Freie Universität Berlin has developed a means of calculating the ground state of the equation with artificial intelligence (AI), according to recent study results published in the journal Nature Chemistry. The deep learning method developed by German researchers is capable of achieving an unprecedented combination of computational efficiency and accuracy, according to the report. 

AI has transformed many technological and scientific areas, from computer graphics to materials science. “We believe that our approach may significantly impact the future of quantum chemistry,” says Professor Frank Noé, who led the team effort. This deep neural network was designed by the team as a new way of representing the wave functions of electrons.

“Instead of the standard approach of composing the wave function from relatively simple mathematical components, we designed an artificial neural network capable of learning the complex patterns of how electrons are located around the nuclei,” the professor explains.

Dr. Jan Hermann of Freie Universitat Berlin, who designed the key features of the method used by the study, added that a special feature of electronic wave functions is their antisymmetry, meaning that they had to build this property into the neural network for the approach to work.

This feature, known as ‘Pauli’s exclusion principle,’ resulted in the authors titling their method ‘PauliNet.’ Alongside the Pauli exclusion principle, electronic wave functions have other fundamental physical properties and much of the innovative success of PauliNet is that it integrates these properties into the deep neural network, rather than letting deep learning figure them out by simply observing the data.

“Building the fundamental physics into the AI is essential for its ability to make meaningful predictions in the field,” says Noe. “This is really where scientists can make a substantial contribution to AI, and exactly what my group is focused on.”

The post Artificial Intelligence cracks Schrodinger’s equation, study finds appeared first on Artificial Intelligence.

Artificial intelligence has transformed pretty much every industry in which it’s been embraced, including healthcare, the stock markets, and, increasingly, cybersecurity, where it’s being utilized to both enhance human work and strengthen defenses. As a result of recent improvements in machine learning, the dreary work that was once done by people, filtering through apparently unlimited amounts of information searching for threat indicators and anomalies would now be able to be automated. Present day AI’s ability to understand threats, risks and relationships enable it to sift through a generous amount of the noise burdening cybersecurity divisions and surface just the pointers destined to be legitimate.

Indeed, even as AI innovation changes some aspects of cybersecurity, the crossing point of the two remains significantly human. In spite of the fact that it’s maybe unreasonable, humans are upfront in all pieces of the cybersecurity triad: the terrible actors who look to do hurt, the gullible soft targets, and the great on-screen characters who retaliate.

Indeed, even without the approaching phantom of AI, the cybersecurity war zone is frequently hazy to average users and the technologically savvy alike. Including a layer of AI, which contains various innovations that can likewise feel unexplainable to many people, may appear to be doubly unmanageable as well as indifferent. That is on the grounds that in spite of the fact that the cybersecurity battle is once in a while profoundly personal, it’s once in a while pursued face to face.

With an expected 3.5 million cybersecurity positions expected to go unfilled by 2021 and with security ruptures increasing some 80% every year, infusing human knowledge with AI and machine learning tools gets critical to shutting the talent availability gap.

That is one of the recommendations of a report called Trust at Scale, as of late released by cybersecurity organization Synack and citing job and breach data from Cybersecurity Ventures and Verizon reports, individually. Indeed, when ethical human hackers were upheld by AI and machine learning, they became 73% increasingly proficient at identifying and evaluating IT risks and threats.

The advantages of this are twofold: Threats never again slip through the cracks because of fatigue or boredom, and cybersecurity experts are liberated to accomplish more strategic tasks, for example, remediation. Artificial intelligence can likewise be utilized to increase perceivability over the network. It can examine phishing by simulating clicks on email links and analyzing word choice and grammar. It can monitor network communications for endeavored installation of malware, command and control communications, and the presence of suspicious packets. What’s more, it’s changed virus detection from an exclusively signature-based framework which was entangled by issues with reaction time, proficiency, and storage requirements to the period of behavioral analysis, which can distinguish signatureless malware, zero-day exploits, and previously unidentified threats.

In any case, while the conceivable outcomes with AI appear to be unfathomable, the possibility that they could wipe out the role of people in cybersecurity divisions is about as unrealistic as the possibility of a phalanx of Baymaxes supplanting the nation’s doctors. While the ultimate objective of AI is to simulate human functions, for example, problem-solving, learning, planning, and intuition, there will consistently be things that AI can’t deal with (yet), as well as things AI should not handle.

The principal classification incorporates things like creativity, which can’t be viably instructed or customized, and therefore will require the guiding hand of a human. Anticipating that AI should viably and reliably decide the context of an attack may likewise be an unconquerable ask, at any rate for the time being, just like the idea that AI could make new solutions for security issues. At the end of the day, while AI can unquestionably add speed and exactness to tasks generally handled by people, it is poor at extending the scope of such tasks.

As it were, AI’s impact on the field of cybersecurity is the same as its effect on different disciplines, in that individuals frequently terribly overestimate what AI can do. They don’t comprehend that AI often works best when it has a restricted application, similar to anomaly detection, versus a broader one, like engineering a solution to a threat. In contrast to people, AI needs inventiveness. It isn’t inventive. It isn’t cunning. It regularly neglects to consider context and memory, leaving it incapable to decipher occasions like a human mind does.

In a meeting with VentureBeat, LogicHub CEO and cofounder Kumar Saurabh showed the requirement for human analysts with a kind of John Henry test for automated threat detection. “A few years ago, we did an examination,” he said. This included arranging a specific amount of information, a trifling sum for an AI model to filter through, yet a sensibly huge sum for a human analyst to perceive how teams utilizing automated frameworks would pass against people in threat detection.

The eventual fate of cybersecurity will be loaded with threats we can’t consider today. Yet, with vigilance and hard work, the blend of man and machine can do what neither can do alone, structure an integral team equipped for upholding order and fighting the forces of evil.

The post THE COMBINATION OF HUMANS AND ARTIFICIAL INTELLIGENCE IN CYBER SECURITY appeared first on Artificial Intelligence.