Training machine leaning algorithms on augmented data fromdifferent related sources is a challenging task. This problemarises in several applications, such as the Internet of Things(IoT), where data may be collected from devices with differentsettings. The learned model on such datasets can generalizepoorly due to distribution bias. In this paper we considerthe problem of classifying unseen datasets, given several labeledtraining samples drawn from similar distributions. Weexploit the intrinsic structure of samples in a latent subspaceand identify landmarks, a subset of training instances fromdifferent sources that should be similar. Incorporating subspacelearning and landmark selection enhances generalizationby alleviating the impact of noise and outliers, as well asimproving efficiency by reducing the size of the data. However,since addressing the two issues simultaneously resultsin an intractable problem, we relax the objective functionby leveraging the theory of nonlinear projection and solve atractable convex optimisation. Through comprehensive analysis,we show that our proposed approach outperforms stateof-the-art results on several benchmark datasets, while keepingthe computational complexity low.

Metric learning has been widely employed, especially in various computer vision tasks, with the fundamental assumption that all samples (e.g., regions/superpixels in images/videos) are independent and identically distributed (IID). However, since the samples are usually spatially-connected or temporally-correlated with their physically-connected neighbours, they are not IID (non-IID for short), which cannot be directly handled by existing methods. Thus, we propose to learn and integrate non-IID metrics (NIME). To incorporate the non-IID spatial/temporal relations, instead of directly using non-IID features and metric learning as previous methods, NIME first builds several non-IID representations on original (non-IID) features by various graph kernel functions, and then automatically learns the metric under the best combination of various non-IID representations. NIME is applied to solve two typical computer vision tasks: interactive image segmentation and histology image identification. The results show that learning and integrating non-IID metrics improves the performance, compared to the IID methods. Moreover, our method achieves results comparable or better than that of the state-of-the-arts.

Countries are amassing cyberweaponry on an unprecedented scale and reconfiguring militaries to meet the threat of cyberwar. Autonomous weapons are being increasingly sought my militaries around the world, but experts fear the worst. AUTONOMOUS robots with the ability to make life or death decisions and snuff out the enemy could very soon be a common feature of warfare, as a new-age arms race between world powers heats up. Harnessing artificial intelligence -- and weaponising it for the battlefield and to gain advantage in cyber warfare -- has the US, Chinese, Russian and other governments furiously working away to gain the edge over their global counterparts. But researchers warn of the incredible dangers involved and the "terrifying future" we risk courting.

Summary: Here's some background on how 3rd generation Spiking Neural Nets are progressing and news about a first commercial rollout. Recently we wrote about the development of AI and neural nets beyond the second generation Convolutional and Recurrent Neural Nets (CNNs / RNNs) which have come on so strong and dominate the current conversation about deep learning. Our research shows that the next generation of neural nets is most likely to be led by Spiking Neural Nets (SNNs) that are a return to the'strong' AI tradition and closely mimic actual brain function. Unlike CNNs that fire signals to every one of their deep layer connections every time, SNNs are modeled after the fact that in the brain neurons do not constantly communicate with one another. Rather they communicate in spikes of signals or more correctly short trains of spiking signals.

Air New Zealand is dipping its toes into artificial intelligence, launching a customer service chatbot that helps passengers with common queries. The airline hopes Oscar, full name Bravo Oscar Tango, will become a "virtual travel assistant", helping passengers through every step of their journey. Oscar will initially help customers with commonly asked queries, which Air New Zealand says will save them time and offer a more personalised experience than searching a traditional Frequently Asked Questions section online. As with other artificial intelligence (AI) technology, Oscar will learn based on the conversations - verbal and text - people have with him, becoming more user-friendly and helpful the more he interacts. Air New Zealand chief digital officer Avi Golan said Oscar had been launched as a beta or early stage product allowing customers to play an active role in training him.

The Universitat Autònoma de Barcelona Research Park has a new company: a spin-off of the UAB and the Higher Council for Scientific Research (CSIC). MusicStrands uses artificial intelligence techniques to provide people with music recommendations. This initiative is the first and only one to use tags applied to music; tags are labels that people can attach on the music they like for easy retrieval later. Tags also make it easy to discover playlists by keying on interesting tags supplied by other users; in addition, tags can help anyone organize playlists by common features. Users of the MusicStrands website have access to a directory of 3.9 million songs.

Gordon Bell will never forget what I look like. He'll never forget what I sound like, either. Actually, he'll never forget a single detail about me. That's because when I first met the affable 72-year-old computer scientist at the offices of Microsoft Research Labs, in Redmond, Washington, he was carefully recording my every move. He had a tiny bug-eyed camera around his neck, and a small audio recorder at his elbow. As we chatted about various topics--Australian jazz musicians, his futuristic cell phone, the Seattle area's gorgeous weather--Bell's gear quietly logged my every gesture and all my blathering small talk, snapping a picture every 60 seconds. Back at his office, his computer had carefully archived every document related to me: all the email I'd sent him, copies of my articles he'd read, pages he'd surfed on my blog. "Oh, I've got everything," Bell said cheerily. And when I saw him the next day, down in his cramped personal office in San Francisco, he offered to give me a glimpse of the memories he'd collected. He plunked down in front of his computer, pulled up a browser, typed in "Clive Fast Company," and there they were: Hundreds of pictures of the meeting scrolled by on his screen, and the sound of our day-old conversation filled the room. It was a deeply strange feeling. My random chitchat is being preserved? He nodded, pointing to a mundane Dell computer parked beneath his desk. Because I'm not the only thing Gordon Bell will never forget. His goal is never to forget anything.

Let's get the basics over with," W said to M when they met on a 4-minute speed date. I am fresh from the shower, wrapped in just a towel and smelling of mild herbal soaps (both shower and soaps are required), standing at the door to the tank. It resembles a shower door--knee-high, sliding--and opens to reveal a...READ MORE They talked about where they were from (she hailed from Iowa, he from New Jersey), life in a small town, and the transition to college. An eavesdropper would have been hard-pressed to detect a romantic spark in this banal back-and-forth. Yet when researchers, who had recorded the exchange, ran it through a language-analysis program, it revealed what W and M confirmed to be true: They were hitting it off. The researchers weren't interested in what the daters discussed, or even whether they seemed to share personality traits, backgrounds, or interests.

AIED is an interdisciplinary community at the frontiers of the fields of computer science, education and psychology. It promotes rigorous research and development of interactive and adaptive learning environments for learners of all ages, across all domains. The society brings together a community of members in the field through the organization of Conferences, a Journal, and other activities of interest. The International AIED Society is governed by an Executive Committee according to the IAIED Constitution, which seeks to support AI in Education developments throughout the international community. Membership statistics show that over 1000 members from 40 countries have joined since the Society's launch on January 1 1997.

Autonomous weapons are being increasingly sought my militaries around the world, but experts fear the worst. AUTONOMOUS robots with the ability to make life or death decisions and snuff out the enemy could very soon be a common feature of warfare, as a new-age arms race between world powers heats up. Harnessing artificial intelligence -- and weaponising it for the battlefield and to gain advantage in cyber warfare -- has the US, Chinese, Russian and other governments furiously working away to gain the edge over their global counterparts. But researchers warn of the incredible dangers involved and the "terrifying future" we risk courting. "The arms race is already starting," said Professor Toby Walsh from UNSW's School of Computer Science and Engineering.