Samuel Greengard is an author and journalist based in West Linn, OR, USA.

The first- and second-generation Nissan GT-R sold for four years, from 1969 to 1973. The R32 to R34 generations covered 13 years, from 1989-2002. The current R35 generation, already 12 years into its run, will shuffle its bones perhaps as long as the first five versions combined. A lot's happened in the last dozen years, so we can expect enormous changes from the next GT-R. Top Gear spoke to Philippe Klein, Nissan's chief planning officer, about what's on the cards.

Deep learning models have demonstrated outstanding performance in several problems, but their training process tends to require immense amounts of computational and human resources for training and labeling, constraining the types of problems that can be tackled. Therefore, the design of effective training methods that require small labeled training sets is an important research direction that will allow a more effective use of resources.Among current approaches designed to address this issue, two are particularly interesting: data augmentation and active learning. Data augmentation achieves this goal by artificially generating new training points, while active learning relies on the selection of the "most informative" subset of unlabeled training samples to be labelled by an oracle. Although successful in practice, data augmentation can waste computational resources because it indiscriminately generates samples that are not guaranteed to be informative, and active learning selects a small subset of informative samples (from a large un-annotated set) that may be insufficient for the training process. In this paper, we propose a Bayesian generative active deep learning approach that combines active learning with data augmentation -- we provide theoretical and empirical evidence (MNIST, CIFAR-$\{10,100\}$, and SVHN) that our approach has more efficient training and better classification results than data augmentation and active learning.

Today, Alphabet's Wing division became the first drone delivery company to receive its Air Carrier Certification from the US Federal Aviation Administration (FAA). The certification means Wing can begin a commercial drone delivery service, and the company hopes to launch its first delivery trial later this year. Over the next several months, Wing will work with the FAA's Unmanned Aircraft System Integration Pilot Program (UAS IPP) in Southwest Virginia. It will soon begin reaching out to residents and businesses in the Blacksburg and Christiansburg, Virginia, areas to demonstrate its technology and to gather feedback. This has been years in the making.

The Wing company, a Google spinoff, has won federal approval to operate its drone delivery system as an airline in the U.S. Wing hide caption The Wing company, a Google spinoff, has won federal approval to operate its drone delivery system as an airline in the U.S. The Federal Aviation Administration has certified Alphabet's Wing Aviation to operate as an airline, in a first for U.S. drone delivery companies. Wing, which began as a Google X project, has been testing its autonomous drones in southwest Virginia and elsewhere. "Air Carrier Certification means that we can begin a commercial service delivering goods from local businesses to homes in the United States," Wing said in a statement posted to the Medium website. The company has touted many advantages of using unmanned drones to deliver packages, from reducing carbon emissions and road congestion to increasing connections between communities and local businesses. "This is an important step forward for the safe testing and integration of drones into our economy. Safety continues to be our Number One priority as this technology continues to develop and realize its full potential," Secretary of Transportation Elaine L. Chao said in a statement from the agency.

Convolution operations designed for graph-structured data usually utilize the graph Laplacian, which can be seen as message passing between the adjacent neighbors through a generic random walk. In this paper, we propose PAN, a new graph convolution framework that involves every path linking the message sender and receiver with learnable weights depending on the path length, which corresponds to the maximal entropy random walk. PAN generalizes the graph Laplacian to a new transition matrix we call \emph{maximal entropy transition} (MET) matrix derived from a path integral formalism. Most previous graph convolutional network architectures can be adapted to our framework, and many variations and derivatives based on the path integral idea can be developed. Experimental results show that the path integral based graph neural networks have great learnability and fast convergence rate, and achieve state-of-the-art performance on benchmark tasks.

This paper describes a prototype system that integrates social media analysis into the European Flood Awareness System (EFAS). This integration allows the collection of social media data to be automatically triggered by flood risk warnings determined by a hydro-meteorological model. Then, we adopt a multi-lingual approach to find flood-related messages by employing two state-of-the-art methodologies: language-agnostic word embeddings and language-aligned word embeddings. Both approaches can be used to bootstrap a classifier of social media messages for a new language with little or no labeled data. Finally, we describe a method for selecting relevant and representative messages and displaying them back in the interface of EFAS.

Gradient Boosting Decision Tree (GBDT) are popular machine learning algorithms with implementations such as LightGBM and in popular machine learning toolkits like Scikit-Learn. Many implementations can only produce trees in an offline manner and in a greedy manner. We explore ways to convert existing GBDT implementations to known neural network architectures with minimal performance loss in order to allow decision splits to be updated in an online manner and provide extensions to allow splits points to be altered as a neural architecture search problem. We provide learning bounds for our neural network.

Complex-valued representations have demonstrated promising results on modeling relational data, i.e., knowledge graphs. This paper proposes a new knowledge graph embedding method. More concretely, we move beyond standard complex representations, adopting expressive hypercomplex representations for learning representations of entities and relations. Hypercomplex embeddings, or Quaternion embeddings (QuatE), are complex valued embeddings with three imaginary components. Different from standard complex (Hermitian) inner product, latent interdependencies (between all components) are aptly captured via the Hamilton product in Quaternion space, encouraging a more efficient and expressive representation learning process. Moreover, Quaternions are intuitively desirable for smooth and pure rotation in vector space, preventing noise from sheer/scaling operators. Finally, Quaternion inductive biases enjoy and satisfy the key desiderata of relational representation learning (i.e., modeling symmetry, anti-symmetry and inversion). Experimental results demonstrate that QuatE achieves state-of-the-art performance on four well-established knowledge graph completion benchmarks.

The fear of robots coming for your job is one of the many challenges confronting 21st-century workers, but the machines aren't ready to take on every industry just yet. Bridgewater Associates, the massive hedge fund founded by legendary investor Ray Dalio, just released a report on the changing relationship between labour and capital in the US. One of the big factors the Bridgewater authors highlighted was the ongoing rise in automation across industries, which they noted could be a support for corporate profits in the years to come as more efficient robots and software potentially replace slower and error-prone human labour. Bridgewater cited a 2016 report from consulting firm McKinsey & Company that looked at which industries in the US were most susceptible to being automated. The McKinsey report used data from the Department of Labour to estimate how much time workers in various industry sectors spent doing different types of tasks, and which of those tasks could, theoretically, be automated using present technology.