In this paper, we presented a novel semi-supervised one-class classification algorithm which assumes that class is linearly separable from other elements. We proved theoretically that class is linearly separable if and only if it is maximal by probability within the sets with the same mean. Furthermore, we presented an algorithm for identifying such linearly separable class utilizing linear programming. We described three application cases including an assumption of linear separability, Gaussian distribution, and the case of linear separability in transformed space of kernel functions. Finally, we demonstrated the work of the proposed algorithm on the USPS dataset and analyzed the relationship of the performance of the algorithm and the size of the initially labeled sample.

In the present paper, we studied a Dynamic Stochastic Block Model (DSBM) under the assumptions that the connection probabilities, as functions of time, are smooth and that at most $s$ nodes can switch their class memberships between two consecutive time points. We estimate the edge probability tensor by a kernel-type procedure and extract the group memberships of the nodes by spectral clustering. The procedure is computationally viable, adaptive to the unknown smoothness of the functional connection probabilities, to the rate $s$ of membership switching and to the unknown number of clusters. In addition, it is accompanied by non-asymptotic guarantees for the precision of estimation and clustering.

We describe the SemEval task of extracting keyphrases and relations between them from scientific documents, which is crucial for understanding which publications describe which processes, tasks and materials. Although this was a new task, we had a total of 26 submissions across 3 evaluation scenarios. We expect the task and the findings reported in this paper to be relevant for researchers working on understanding scientific content, as well as the broader knowledge base population and information extraction communities.

Nesterov's momentum trick is famously known for accelerating gradient descent, and has been proven useful in building fast iterative algorithms. However, in the stochastic setting, counterexamples exist and prevent Nesterov's momentum from providing similar acceleration, even if the underlying problem is convex. We introduce $\mathtt{Katyusha}$, a direct, primal-only stochastic gradient method to fix this issue. It has a provably accelerated convergence rate in convex (off-line) stochastic optimization. The main ingredient is $\textit{Katyusha momentum}$, a novel "negative momentum" on top of Nesterov's momentum. It can be incorporated into a variance-reduction based algorithm and speed it up, both in terms of $\textit{sequential and parallel}$ performance. Since variance reduction has been successfully applied to a growing list of practical problems, our paper suggests that in each of such cases, one could potentially try to give Katyusha a hug.

Deep learning has become a powerful and popular tool for a variety of machine learning tasks. However, it is extremely challenging to understand the mechanism of deep learning from a theoretical perspective. In this work, we study robustness of a deep network in its generalization capability against removal of a certain number of connections between layers. A critical value of this number is observed to separate a robust (redundant) regime from a sensitive regime. This empirical behavior is captured qualitatively by a random active path model, where the path from input to output is randomly and independently constructed. The empirical critical value corresponds to termination of a paramagnetic phase in the random active path model. Furthermore, this model provides us qualitative understandings about dropconnect probability commonly used in the dropconnect algorithm and its relationship with the redundancy phenomenon. In addition, we combine the dropconnect and the random feedback alignment for feedforward and backward pass in a deep network training respectively, and observe fast learning and improved test performance in classifying a benchmark handwritten digits dataset.

In 2001, a group of Physicists were awarded the Nobel prize in Physics for creating an experiment that produced the Bose Einstein Condensate(BEC). The BEC is a state of Matter in an extremely cold state, close to absolute zero(that is, very near 0 K or 273.15 C), first theorized by Satyendra Nath Bose and Albert Einstein in 1925. In the 2001 Noble Prize winning experiment, the physicists created the first BEC in a lab by shooting multiple lasers at Gas particles from different directions. After meticulous calculations and planning, they carefully calibrated a series of lasers to achieve this.

An AI research group backed by some of the biggest names in tech announced today that another giant was joining its project. Partnership on AI wrote in a blog post that Apple would become a founding member. Apple will now work alongside original founding members Amazon, DeepMind/Google, Facebook, IBM, and Microsoft in a high-profile display of cooperation among companies that can often be heated rivals. "Diversity of thought across the organization is crucial to ensure that we effectively explore and address the influences of AI on people and society, provide guidance on AI best practices, and seek to advance the public's understanding of AI," says the blog post. "We are committed to having balanced representation at the leadership, executive, and operations levels."

Apple's rumored Siri speaker could be announced as soon as June at the Worldwide Developers Conference, according to a note by KGI Securities analyst Ming-Chi Kuo obtained by MacRumors. Kuo said there is an "over 50 percent chance" the speaker will be revealed at WWDC, which will be held June 5-9. "We believe there is an over 50 percent chance that Apple will announce its first home AI [artificial intelligence] product at WWDC in June and start selling in the [second half of 2017] in order to compete with the new Amazon Echo models to be launched," Kuo said in the note. The analyst also revealed the Siri speaker will cost more than the Amazon Echo. Apple's rumored speaker will supposedly support AirPlay, which had been rumored before, and will have "excellent" acoustics performance.

Here at The Human OS, we are slightly obsessed with matchups between artificial intelligence and doctors. In many experiments (though not yet in many clinics), AI systems are showing great promise in diagnosing diseases, analyzing medical images, and predicting health outcomes. They've even performed better than human doctors in certain tasks like surgical stitching and diagnosing autism in infants. Now, in the latest win for AI medicine, researchers at the University of Nottingham in the UK created a system that scanned patients' routine medical data and predicted which of them would have heart attacks or strokes within 10 years. When compared to the standard method of prediction, the AI system correctly predicted the fates of 355 more patients.

The eyes of male net-casting spiders shrink by 25 per cent when they've entered adulthood, but females' eyes increase in diameter by 21 per cent. Net-casting spiders use their secondary eyes for motion detection to catch prey at night by entangling them using a silk-spun net. Researchers say that the reason for the spiders' change in eye size may have to do with their hunting strategies - males lose the ability to spin food-capturing nets as they become adults, so they don't need such large eyes, while females retain their hunting abilities. Pictured top left is a females' eyes before transitioning to adulthood, and bottom left after maturing to adulthood. Pictured top right is a males' eyes before maturing, and bottom right after maturing.