The following is an opinion piece written by Ian Jefferies, president and CEO of the Association of American Railroads. Opinions are the author's own. The White House recently issued draft principles for governing the use of artificial intelligence across sectors, including transportation. While a recent report noted the guidance may be too vague to produce substantive benefits, the larger point is clear. Various forms of AI are here to stay and will only become more ubiquitous.

By Robbin Laird During my visit to Australia last October, I had a chance to talk to a number of people about the evolving approach in Australia to maritime remotes and their evolving role within the "fifth generation" warfare approach or what I refer to as building a distributed integratable force or an integrated distributed […]

Machine learning models have demonstrated vulnerability to adversarial attacks, more specifically misclassification of adversarial examples. In this paper, we propose a one-off and attack-agnostic Feature Manipulation (FM)-Defense to detect and purify adversarial examples in an interpretable and efficient manner. The intuition is that the classification result of a normal image is generally resistant to non-significant intrinsic feature changes, e.g., varying thickness of handwritten digits. In contrast, adversarial examples are sensitive to such changes since the perturbation lacks transferability. To enable manipulation of features, a combo-variational autoencoder is applied to learn disentangled latent codes that reveal semantic features. The resistance to classification change over the morphs, derived by varying and reconstructing latent codes, is used to detect suspicious inputs. Further, combo-VAE is enhanced to purify the adversarial examples with good quality by considering both class-shared and class-unique features. We empirically demonstrate the effectiveness of detection and the quality of purified instance. Our experiments on three datasets show that FM-Defense can detect nearly $100\%$ of adversarial examples produced by different state-of-the-art adversarial attacks. It achieves more than $99\%$ overall purification accuracy on the suspicious instances that close the manifold of normal examples.

Choosing the technique that is the best at forecasting your data, is a problem that arises in any forecasting application. Decades of research have resulted into an enormous amount of forecasting methods that stem from statistics, econometrics and machine learning (ML), which leads to a very difficult and elaborate choice to make in any forecasting exercise. This paper aims to facilitate this process for high-level tactical sales forecasts by comparing a large array of techniques for 35 times series that consist of both industry data from the Coca-Cola Company and publicly available datasets. However, instead of solely focusing on the accuracy of the resulting forecasts, this paper introduces a novel and completely automated profit-driven approach that takes into account the expected profit that a technique can create during both the model building and evaluation process. The expected profit function that is used for this purpose, is easy to understand and adaptable to any situation by combining forecasting accuracy with business expertise. Furthermore, we examine the added value of ML techniques, the inclusion of external factors and the use of seasonal models in order to ascertain which type of model works best in tactical sales forecasting. Our findings show that simple seasonal time series models consistently outperform other methodologies and that the profit-driven approach can lead to selecting a different forecasting model.

Knowledge Graphs (KGs) have found many applications in industry and academic settings, which in turn, have motivated considerable research efforts towards large-scale information extraction from a variety of sources. Despite such efforts, it is well known that even state-of-the-art KGs suffer from incompleteness. Link Prediction (LP), the task of predicting missing facts among entities already a KG, is a promising and widely studied task aimed at addressing KG incompleteness. Among the recent LP techniques, those based on KG embeddings have achieved very promising performances in some benchmarks. Despite the fast growing literature in the subject, insufficient attention has been paid to the effect of the various design choices in those methods. Moreover, the standard practice in this area is to report accuracy by aggregating over a large number of test facts in which some entities are over-represented; this allows LP methods to exhibit good performance by just attending to structural properties that include such entities, while ignoring the remaining majority of the KG. This analysis provides a comprehensive comparison of embedding-based LP methods, extending the dimensions of analysis beyond what is commonly available in the literature. We experimentally compare effectiveness and efficiency of 16 state-of-the-art methods, consider a rule-based baseline, and report detailed analysis over the most popular benchmarks in the literature.

How should government and society come together to address the challenge of regulating artificial intelligence? What approaches and tools will promote innovation, protect society from harm and build public trust in AI? Artificial intelligence (AI) is a key driver of the Fourth Industrial Revolution. Algorithms are already being applied to improve predictions, optimize systems and drive productivity in many other sectors. However, early experience shows that AI can create serious challenges. Without proper oversight, AI may replicate or even exacerbate human bias and discrimination, cause potential job displacement, and lead to other unintended and harmful consequences.

WELLINGTON – Mike Moore, who served as New Zealand's prime minister before leading the World Trade Organization during a tumultuous time when thousands protested in Seattle riots, died early Sunday. He died at his home in Auckland, his wife Yvonne Moore said. He had suffered a number of health complications since having a stroke five years ago. Moore was an advocate for both advancing the rights of blue-collar workers and for expanding international trade, a combination which, to some, seemed at odds with itself. Although he had a long political career in New Zealand, Moore's tenure as prime minister was brief: just two months in 1990 before he was defeated in an election.

Human knowledge provides a formal understanding of the world. Knowledge graphs that represent structural relations between entities have become an increasingly popular research direction towards cognition and human-level intelligence. In this survey, we provide a comprehensive review on knowledge graph covering overall research topics about 1) knowledge graph representation learning, 2) knowledge acquisition and completion, 3) temporal knowledge graph, and 4) knowledge-aware applications, and summarize recent breakthroughs and perspective directions to facilitate future research. We propose a full-view categorization and new taxonomies on these topics. Knowledge graph embedding is organized from four aspects of representation space, scoring function, encoding models and auxiliary information. For knowledge acquisition, especially knowledge graph completion, embedding methods, path inference and logical rule reasoning are reviewed. We further explore several emerging topics including meta relational learning, commonsense reasoning, and temporal knowledge graphs. To facilitate future research on knowledge graphs, we also provide a curated collection of datasets and open-source libraries on different tasks. In the end, we have a thorough outlook on several promising research directions.

The evaluation of machine learning (ML) pipelines is essential during automatic ML pipeline composition and optimisation. The previous methods such as Bayesian-based and genetic-based optimisation, which are implemented in Auto-Weka, Auto-sklearn and TPOT, evaluate pipelines by executing them. Therefore, the pipeline composition and optimisation of these methods requires a tremendous amount of time that prevents them from exploring complex pipelines to find better predictive models. To further explore this research challenge, we have conducted experiments showing that many of the generated pipelines are invalid, and it is unnecessary to execute them to find out whether they are good pipelines. To address this issue, we propose a novel method to evaluate the validity of ML pipelines using a surrogate model (AVATAR). The AVATAR enables to accelerate automatic ML pipeline composition and optimisation by quickly ignoring invalid pipelines. Our experiments show that the AVATAR is more efficient in evaluating complex pipelines in comparison with the traditional evaluation approaches requiring their execution.

Perth City Council has reportedly been filming and tracking people moving around parts of the city without their knowledge. In what the council calls a trial, a network of 30 cameras with facial recognition technology have been deployed across East Perth. This has quietly gone on for six months. The cameras use deep-learning artificial intelligence (AI) to recognise faces and vehicles, and to count passing people – a form of population control which China widely employs, and is criticised for by human rights groups. But in Perth – the third Australian city to invest in the technology – many residents were unaware of the trial before it started.