Lifeboat Foundation

“We want a new space race—space races are exciting,” declared SpaceX founder Elon Musk after the successful inaugural flight last year of the Falcon Heavy, the most powerful rocket since the Space Shuttle.

Hawks and headline writers think space races are exciting too, especially the “new space race” between China and the United States. That’s why they keep referring to it—even though it doesn’t exist.

Historic changes are indeed afoot in the space sector. Private crewed spaceflight is about to come of age. Mobile robotic spacecraft are being built to rendezvous with satellites to service them. Vast swarms of broadband satellites are set to make the Internet truly global for the first time, and increase the number of spacecraft in orbit tenfold. Back on Earth, satellite imagery fed through artificial intelligence algorithms promises powerful insights into all manner of human activity. Dozens of countries are active in space and the number is growing all the time. The tired trope of the superpower space race does little to make sense of all this.

Uncovering trolls and malicious or spammy accounts on social media is increasingly difficult as the miscreants find more and more ways to camouflage themselves as seemingly legitimate. Writing in the International Journal of Intelligent Engineering Informatics, researchers in India have developed an algorithm based on ant-colony optimization that can effectively detect accounts that represent a threat to normal users.

Asha Kumari and Balkishan Department of Computer Science and Applications at Maharshi Dayanand University, in Rohtak, India, explain that the connections between twitter users are analogous to the pheromone chemical communication between ants and this can be modeled in an algorithm based on how ant colonies behave to reveal the strongest connections in the twitter network and so uncover the accounts that one might deem as threatening to legitimate users.

The team’s tests on their system were successful in terms of precision, recall, f-measure, true-positive rate, and false-positive rate based on 26 features examined by the system played against almost 41,500 user accounts attracted to honeypots. Moreover, they report that the approach is superior to existing techniques. The team adds that they hope to be able to improve the system still further by adding so-called machine learning into the algorithm so that it can be trained to better identify threatening accounts based on data from known threats and legitimate accounts.

Over the last few years, rapid progress in AI has enabled our smartphones, social networks, and search engines to understand our voice, recognize our faces, and identify objects in our photos with very good accuracy. These dramatic improvements are due in large part to the emergence of a new class of machine learning methods known as Deep Learning.

Animals and humans can learn to see, perceive, act, and communicate with an efficiency that no Machine Learning method can approach. The brains of humans and animals are “deep”, in the sense that each action is the result of a long chain of synaptic communications (many layers of processing). We are currently researching efficient learning algorithms for such “deep architectures”. We are currently concentrating on unsupervised learning algorithms that can be used to produce deep hierarchies of features for visual recognition. We surmise that understanding deep learning will not only enable us to build more intelligent machines but will also help us understand human intelligence and the mechanisms of human learning. http://www.cs.nyu.edu/~yann/research/deep/

But in the last few years, AI has changed the game. Deep-learning algorithms excel at quickly finding patterns in reams of data, which has sped up key processes in scientific discovery. Now, along with these software improvements, a hardware revolution is also on the horizon.

Yesterday Argonne announced that it has begun to test a new computer from the startup Cerebras that promises to accelerate the training of deep-learning algorithms by orders of magnitude. The computer, which houses the world’s largest chip, is part of a new generation of specialized AI hardware that is only now being put to use.

“We’re interested in accelerating the AI applications that we have for scientific problems,” says Rick Stevens, Argonne’s associate lab director for computing, environment, and life sciences. “We have huge amounts of data and big models, and we’re interested in pushing their performance.”

Barbara Liskov pioneered the modern approach to writing code. She warns that the challenges facing computer science today can’t be overcome with good design alone.

Maybe interesting for this group too.

Visit http://TED.com to get our entire library of TED Talks, transcripts, translations, personalized Talk recommendations and more.

Continue reading “The danger of AI is weirder than you think | Janelle Shane” »

Most humans can learn how to complete a given task by observing another person perform it just once. Robots that are programmed to learn by imitating humans, however, typically need to be trained on a series of human demonstrations before they can effectively reproduce the desired behavior.

Researchers were recently able to teach robots to execute new tasks by having them observe a single human demonstration, using meta-learning approaches. However, these learning techniques typically require real-world data that can be expensive and difficult to collect.

Continue reading “An imitation learning approach to train robots without the need for real human demonstrations” »

Artificial intelligence can be used to predict molecular wave functions and the electronic properties of molecules. This innovative AI method developed by a team of researchers at the University of Warwick, the Technical University of Berlin and the University of Luxembourg, could be used to speed-up the design of drug molecules or new materials.

Artificial intelligence and machine learning algorithms are routinely used to predict our purchasing behavior and to recognize our faces or handwriting. In scientific research, Artificial Intelligence is establishing itself as a crucial tool for scientific discovery.

In chemistry, AI has become instrumental in predicting the outcomes of experiments or simulations of quantum systems. To achieve this, AI needs to be able to systematically incorporate the fundamental laws of physics.

A pair of mathematicians from Australia and France have devised an alternative way to multiply numbers together, while solving an algorithmic puzzle that has perplexed some of the greatest math minds for almost half a century.

For most of us, the way we multiply relatively small numbers is by remembering our times tables – an incredibly handy aid first pioneered by the Babylonians some 4,000 years ago.

Continue reading “Mathematicians Have Discovered an Entirely New Way to Multiply Large Numbers” »