We study the issue of PAC-Bayesian domain adaptation: We want to learn, from a source domain, a majority vote model dedicated to a target one. Our theoretical contribution brings a new perspective by deriving an upper-bound on the target risk where the distributions' divergence-- expressed as a ratio--controls the tradeoff between a source error measure and the target voters' disagreement. Our bound suggests that one has to focus on regions where the source data is informative. From this result, we derive a PAC-Bayesian generalization bound, and specialize it to linear classifiers. Then, we infer a learning algorithm and perform experiments on real data.

Unstructured data refers to information that does not have a predefined data model or is not organized in a pre-defined manner. Loosely speaking, unstructured data refers to text data that is generated by humans. In after-sales service businesses, there are two main sources of unstructured data: customer complaints, which generally describe symptoms, and technician comments, which outline diagnostics and treatment information. A legitimate customer complaint can eventually be tracked to a failure or a claim. However, there is a delay between the time of a customer complaint and the time of a failure or a claim. A proactive strategy aimed at analyzing customer complaints for symptoms can help service providers detect reliability problems in advance and initiate corrective actions such as recalls. This paper introduces essential text mining concepts in the context of reliability analysis and a method to detect emerging reliability issues. The application of the method is illustrated using a case study.

In this paper, we present an approach for learning a visual representation from the raw spatiotemporal signals in videos. Our representation is learned without supervision from semantic labels. We formulate our method as an unsupervised sequential verification task, i.e., we determine whether a sequence of frames from a video is in the correct temporal order. With this simple task and no semantic labels, we learn a powerful visual representation using a Convolutional Neural Network (CNN). The representation contains complementary information to that learned from supervised image datasets like ImageNet. Qualitative results show that our method captures information that is temporally varying, such as human pose. When used as pre-training for action recognition, our method gives significant gains over learning without external data on benchmark datasets like UCF101 and HMDB51. To demonstrate its sensitivity to human pose, we show results for pose estimation on the FLIC and MPII datasets that are competitive, or better than approaches using significantly more supervision. Our method can be combined with supervised representations to provide an additional boost in accuracy.

Many people spend their childhood peering up into the vast expanse of the sky, dreaming of growing up to become an astronaut. But these dreams could be dashed as the idea of people venturing into space will one day become a distant memory, according to a report published today. Robots will eventually have enough capabilities to replace humans and other animals on space missions, experts have said. Robots will eventually have enough capabilities to replace humans and other animals on space missions, experts have said. Russia is planning to send robots to the ISS to do jobs that are too dangerous for astronauts.

In a village in western Africa, a tsetse fly bites a human, injecting a swarm of the deadly sleeping sickness-causing parasite Trypanosoma brucei into the bloodstream. Once inside its human host, the parasite spreads through the body, rapidly using its flexible flagellum to propel itself, eventually hiding the structure inside its body to evade the host's immune system once it is safely ensconced. Imagine a swarm of microscopic bots that mimics Trypanosoma brucei's behavior. In this case, though, instead of killing their hosts, the bots are designed to circulate through the bloodstream to perform highly-targeted drug deliveries and carry out invasive and delicate surgeries that may otherwise be too risky to perform. This is what a team of scientists at the Swiss Federal Institute of Technology in Zurich (ETHZ) and the Swiss Federal Institute of Technology in Lausanne (EPFL) are working toward.

Australian bank Westpac is to trial the use of artificial intelligence (AI) in its digital banking systems, as it looks to automate customers' queries. With the rise of digital banking, Westpac's general manager of consumer digital, Travis Tyler, says it is looking at using "bots" to respond to customers' simple questions. One example includes the bank working on a "proof of concept" over the next six months for a digital system to provide answers to consumer questions about the best deposit rates available. In an interview with the Sydney Morning Herald, Tyler says: "If your term deposit is rolling over, and you simply ask, 'What's the best rate, this is what I want to achieve?', it will come back with the best options and you can simply say, 'Yeah, book it.'" Another example cited by Tyler includes answering simple questions about payments between accounts.

A few well-publicized recent papers have tempered the hype surrounding deep learning. The papers identify both that images can be subtly altered to induce misclassification and that seemingly random garbage images can easily be generated which receive high confidence classifications. A wave of press has sensationalized the message. Several blog posts, a YouTube video, and others have amplified and occasionally distorted the results, professing the gullibility of deep networks. Given the hoopla, it's appropriate to examine these findings.

Social media has recently emerged as a premier method to disseminate information online. Through these online networks, tens of millions of individuals communicate their thoughts, personal experiences, and social ideals. We therefore explore the potential of social media to predict, even prior to onset, Major Depressive Disorder (MDD) in online personas. We employ a crowdsourced method to compile a list of Twitter users who profess to being diagnosed with depression. Using up to a year of prior social media postings, we utilize a Bag of Words approach to quantify each tweet. Lastly, we leverage several statistical classifiers to provide estimates to the risk of depression. Our work posits a new methodology for constructing our classifier by treating social as a text-classification problem, rather than a behavioral one on social media platforms. By using a corpus of 2.5M tweets, we achieved an 81% accuracy rate in classification, with a precision score of .86. We believe that this method may be helpful in developing tools that estimate the risk of an individual being depressed, can be employed by physicians, concerned individuals, and healthcare agencies to aid in diagnosis, even possibly enabling those suffering from depression to be more proactive about recovering from their mental health.

We consider clustering problems where the goal is to determine an optimal partition of a given point set in Euclidean space in terms of a collection of affine subspaces. While there is vast literature on heuristics for this kind of problem, such approaches are known to be susceptible to poor initializations and getting trapped in bad local optima. We alleviate these issues by introducing a semidefinite relaxation based on Lasserre's method of moments. While a similiar approach is known for classical Euclidean clustering problems, a generalization to our more general subspace scenario is not straightforward, due to the high symmetry of the objective function that weakens any convex relaxation. We therefore introduce a new mechanism for symmetry breaking based on covering the feasible region with polytopes. Additionally, we introduce and analyze a deterministic rounding heuristic.

Consider the stochastic composition optimization problem where the objective is a composition of two expected-value functions. We propose a new stochastic first-order method, namely the accelerated stochastic compositional proximal gradient (ASC-PG) method, which updates based on queries to the sampling oracle using two different timescales. The ASC-PG is the first proximal gradient method for the stochastic composition problem that can deal with nonsmooth regularization penalty. We show that the ASC-PG exhibits faster convergence than the best known algorithms, and that it achieves the optimal sample-error complexity in several important special cases. We further demonstrate the application of ASC-PG to reinforcement learning and conduct numerical experiments.