Multi-view time series classification aims to fuse the distinctive temporal information from different views to further enhance the classification performance. Existing methods mainly focus on fusing multi-view features at an early stage ( e.g., learning a common representation shared by multiple views). However, these early fusion methods may not fully exploit the view-specific distinctive patterns in high-dimension time series data. Moreover, the intra-view and interview label correlations, which are critical for multi-view classification, are usually ignored in previous works. In this paper, we propose a Global-Local Correlative Channel-A ware Fusion (GLCCF) model to address the aforementioned issues. Particularly, our model extracts global and local temporal patterns by a two-stream structure encoder, captures the intra-view and interview label correlations by constructing a graph based correlation matrix, and extracts the cross-view global patterns via a learnable channel-aware late fusion mechanism, which could be effectively implemented with a convo-lutional neural network. Extensive experiments on two real-world datasets demonstrate the superiority of our approach over the state-of-the-art methods. An ablation study is further provided to show the effectiveness of each model component. Introduction Time series classification has attracted increasing attention recently since temporal data contains more dynamic patterns which cannot be discovered easily.

Graphical causal inference as pioneered by Judea Pearl arose from research on artificial intelligence (AI), and for a long time had little connection to the field of machine learning. This article discusses where links have been and should be established, introducing key concepts along the way. It argues that the hard open problems of machine learning and AI are intrinsically related to causality, and explains how the field is beginning to understand them.

At the Common Good in the Digital Age tech conference recently held in Vatican City, Pope Francis urged Facebook executives, venture capitalists, and government regulators to be wary of the impact of AI and other technologies. "If mankind's so-called technological progress were to become an enemy of the common good, this would lead to an unfortunate regression to a form of barbarism dictated by the law of the strongest," he said. In a related but contextually different conversation, this summer Joy Buolamwini testified before Congress with Rep. Alexandria Ocasio-Cortez (D-NY) that multiple audits found facial recognition technology generally works best on white men and worst on women of color. What these two events have in common is their relationship to power dynamics in the AI ethics debate. Arguments about AI ethics can wage without mention of the word "power," but it's often there just under the surface. In fact, it's rarely the direct focus, but it needs to be. Power in AI is like gravity, an invisible force that influences every consideration of ethics in artificial intelligence. Power provides the means to influence which use cases are relevant; which problems are priorities; and who the tools, products, and services are made to serve. It underlies debates about how corporations and countries create policy governing use of the technology.

Document recommendation systems for locating relevant literature have mostly relied on methods developed a decade ago. This is largely due to the lack of a large offline gold-standard benchmark of relevant documents that cover a variety of research fields such that newly developed literature search techniques can be compared, improved and translated into practice. To overcome this bottleneck, we have established the RElevant LIterature SearcH consortium consisting of more than 1500 scientists from 84 countries, who have collectively annotated the relevance of over 180 000 PubMed-listed articles with regard to their respective seed (input) article/s. The majority of annotations were contributed by highly experienced, original authors of the seed articles. The collected data cover 76% of all unique PubMed Medical Subject Headings descriptors. No systematic biases were observed across different experience levels, research fields or time spent on annotations.

Seventy years ago, science fiction writer Isaac Asimov imagined a world where robots would serve humans in countless ways, and he equipped them with built-in safeguards now known as Asimov's Three Laws of Robotics, to prevent them, among other goals, from ever harming a person. Guaranteeing safe and fair machine behavior is still an issue today, says machine learning researcher and lead author Philip Thomas at the University of Massachusetts Amherst. "When someone applies a machine learning algorithm, it's hard to control its behavior," he points out. This risks undesirable outcomes from algorithms that direct everything from self-driving vehicles to insulin pumps to criminal sentencing, say he and co-authors. Writing in Science, Thomas and his colleagues Yuriy Brun, Andrew Barto and graduate student Stephen Giguere at UMass Amherst, Bruno Castro da Silva at the Federal University of Rio Grande del Sol, Brazil, and Emma Brunskill at Stanford University this week introduce a new framework for designing machine learning algorithms that make it easier for users of the algorithm to specify safety and fairness constraints.

THE THAMES seems to draw people who work on intelligence-gathering. The spooks of MI6 are housed in a funky-looking building overlooking the river. Two miles downstream, in a shared office space near Blackfriars Bridge, lives Arkera, a firm that uses machine-learning technology to sort intelligence from newspapers, websites and other public sources for emerging-market investors. London has the right time zone, between the Americas and Asia. It is a nice place to live.

Despite recent advances in architectures for mobile devices, deep learning computational requirements remains prohibitive for most embedded devices. To address that issue, we envision sharing the computational costs of inference between local devices and the cloud, taking advantage of the compression performed by the first layers of the networks to reduce communication costs. Inference in such distributed setting would allow new applications, but requires balancing a triple trade-off between computation cost, communication bandwidth, and model accuracy. We explore that trade-off by studying the compressibility of representations at different stages of MobileNetV2, showing those results agree with theoretical intuitions about deep learning, and that an optimal splitting layer for network can be found with a simple PCA-based compression scheme.

In this paper, we present a deep neural network (DNN) training approach called the "DeepMimic" training method. Enormous amounts of data are available nowadays for training usage. Yet, only a tiny portion of these data is manually labeled, whereas almost all of the data are unlabeled. The training approach presented utilizes, in a most simplified manner, the unlabeled data to the fullest, in order to achieve remarkable (classification) results. Our DeepMimic method uses a small portion of labeled data and a large amount of unlabeled data for the training process, as expected in a real-world scenario. It consists of a mentor model and a student model. Employing a mentor model trained on a small portion of the labeled data and then feeding it only with unlabeled data, we show how to obtain a (simplified) student model that reaches the same accuracy and loss as the mentor model, on the same test set, without using any of the original data labels in the training of the student model. Our experiments demonstrate that even on challenging classification tasks the student network architecture can be simplified significantly with a minor influence on the performance, i.e., we need not even know the original network architecture of the mentor. In addition, the time required for training the student model to reach the mentor's performance level is shorter, as a result of a simplified architecture and more available data. The proposed method highlights the disadvantages of regular supervised training and demonstrates the benefits of a less traditional training approach.

Speaking at the third annual Digital Workforce Summit in New York City, Gonzalo Gomez Cid, Global Contact Center Director at Telefónica, discussed his company's journey from IVR-based contact centers to AI-driven operations driven by digital labor. Telefónica is a Spanish multinational telecommunications company headquartered in Madrid. It has a presence in 15 countries across Europe and Latin America. In the telco space, it ranks seventh in revenues, sixth in market capitalization and fifth in number of subscribers. Gomez Cid told DWS attendees that Telefónica describes itself as a "company of platforms," including physical assets, networks and IT, and products and services.

Digital channels targeting the mass consumer market are helping insurers swell their client base without the need for traditional intermediaries – but at a cost. One cost is increased risk of fraud, global insurance fraud analytics firm FRISS said during an event in Chile outlining the results of the first fraud survey of its kind covering all Latin America. As technology develops and purchasing habits change, insurers are increasingly leveraging digital channels, allowing consumers to take out policies online, directly from an insurer, in a largely frictionless manner. The trend is forecast to continue in Latin America as insurers seek to keep costs under control, tap what is still an underpenetrated market, and stand out from the crowd. One consequence of this is the sidelining of brokers, whose detailed client knowledge can help prevent fraud, said FRISS, a Dutch firm that provides an AI-powered platform to help P&C insurers combat fraud and which carried out the survey of insurance companies.