Tabular data is the most common data format adopted by our customers ranging from retail, finance to E-commerce, and tabular data classification plays an essential role to their businesses. In this paper, we present Network On Network (NON), a practical tabular data classification model based on deep neural network to provide accurate predictions. Various deep methods have been proposed and promising progress has been made. However, most of them use operations like neural network and factorization machines to fuse the embeddings of different features directly, and linearly combine the outputs of those operations to get the final prediction. As a result, the intra-field information and the non-linear interactions between those operations (e.g. neural network and factorization machines) are ignored. Intra-field information is the information that features inside each field belong to the same field. NON is proposed to take full advantage of intra-field information and non-linear interactions. It consists of three components: field-wise network at the bottom to capture the intra-field information, across field network in the middle to choose suitable operations data-drivenly, and operation fusion network on the top to fuse outputs of the chosen operations deeply. Extensive experiments on six real-world datasets demonstrate NON can outperform the state-of-the-art models significantly. Furthermore, both qualitative and quantitative study of the features in the embedding space show NON can capture intra-field information effectively.

Transformers are ubiquitous in Natural Language Processing (NLP) tasks, but they are difficult to be deployed on hardware due to the intensive computation. To enable low-latency inference on resource-constrained hardware platforms, we propose to design Hardware-Aware Transformers (HAT) with neural architecture search. We first construct a large design space with $\textit{arbitrary encoder-decoder attention}$ and $\textit{heterogeneous layers}$. Then we train a $\textit{SuperTransformer}$ that covers all candidates in the design space, and efficiently produces many $\textit{SubTransformers}$ with weight sharing. Finally, we perform an evolutionary search with a hardware latency constraint to find a specialized $\textit{SubTransformer}$ dedicated to run fast on the target hardware. Extensive experiments on four machine translation tasks demonstrate that HAT can discover efficient models for different hardware (CPU, GPU, IoT device). When running WMT'14 translation task on Raspberry Pi-4, HAT can achieve $\textbf{3}\times$ speedup, $\textbf{3.7}\times$ smaller size over baseline Transformer; $\textbf{2.7}\times$ speedup, $\textbf{3.6}\times$ smaller size over Evolved Transformer with $\textbf{12,041}\times$ less search cost and no performance loss. HAT code is https://github.com/mit-han-lab/hardware-aware-transformers.git

Averting the effects of anthropogenic climate change requires a transition from fossil fuels to low-carbon technology. A way to achieve this is to decarbonize the electricity grid. However, further efforts must be made in other fields such as transport and heating for full decarbonization. This would reduce carbon emissions due to electricity generation, and also help to decarbonize other sources such as automotive and heating by enabling a low-carbon alternative. Carbon taxes have been shown to be an efficient way to aid in this transition. In this paper, we demonstrate how to to find optimal carbon tax policies through a genetic algorithm approach, using the electricity market agent-based model ElecSim. To achieve this, we use the NSGA-II genetic algorithm to minimize average electricity price and relative carbon intensity of the electricity mix. We demonstrate that it is possible to find a range of carbon taxes to suit differing objectives. Our results show that we are able to minimize electricity cost to below \textsterling10/MWh as well as carbon intensity to zero in every case. In terms of the optimal carbon tax strategy, we found that an increasing strategy between 2020 and 2035 was preferable. Each of the Pareto-front optimal tax strategies are at least above \textsterling81/tCO2 for every year. The mean carbon tax strategy was \textsterling240/tCO2.

Having been collected for its primary purpose in patient care, Observational Health Data (OHD) can further benefit patient well-being by sustaining the development of health informatics. However, the potential for secondary usage of OHD continues to be hampered by the fiercely private nature of patient-related data. Generative Adversarial Networks (GAN) have Generative Adversarial Networks (GAN) have recently emerged as a groundbreaking approach to efficiently learn generative models that produce realistic Synthetic Data (SD). However, the application of GAN to OHD seems to have been lagging in comparison to other fields. We conducted a review of GAN algorithms for OHD in the published literature, and report our findings here.

Traditional computational authorship attribution describes a classification task in a closed-set scenario. Given a finite set of candidate authors and corresponding labeled texts, the objective is to determine which of the authors has written another set of anonymous or disputed texts. In this work, we propose a probabilistic autoencoding framework to deal with this supervised classification task. More precisely, we are extending a variational autoencoder (VAE) with embedded Gaussian mixture model to a Student-$t$ mixture model. Autoencoders have had tremendous success in learning latent representations. However, existing VAEs are currently still bound by limitations imposed by the assumed Gaussianity of the underlying probability distributions in the latent space. In this work, we are extending the Gaussian model for the VAE to a Student-$t$ model, which allows for an independent control of the "heaviness" of the respective tails of the implied probability densities. Experiments over an Amazon review dataset indicate superior performance of the proposed method.

Routing of multiple vehicles is an important and difficult problem with applications in the logistic domain [1], especially in the area of customer servicing [2]. In postal services, after-sales services, and in business to business delivery or pick up services one or more vehicles have to be efficiently routed towards customers. If customers can request services over time, the problem becomes dynamic: besides a set of fixed customers, new requests can appear at any point in time. Of course, it is desirable that as many customers as possible are serviced while the tour of any vehicle is kept short. However, it is usually infeasible (due to human resources, labor regulations, or other constraints) to service all customer requests. And clearly, the less customers are left unserviced, the longer the tours become. Thus, the problem is inherently multi-objective. Any efficient solution (smallest maximum tour across all vehicles) is a compromise between the desire to service as many customers as possible (e.g.

"We didn't learn the lesson on SARS and MERS," UK prime minister Boris Johnson said today as he faced questions from the House of Commons Liaison Committee, referencing the government's pandemic planning and a lack of capacity at Public Health England to detect outbreaks of coronavirus around the country. He also said that there would not be an official inquiry to investigate whether his senior aide Dominic Cummings broke lockdown rules. More than 40 Conservative party MPs have now called for Cummings' resignation. During the meeting, Johnson announced that England's test and trace system will be launched tomorrow. Under the new system, contact tracers will ask people who test positive for coronavirus to self-isolate for 14 days, regardless of symptoms, and to provide details of any recent close contacts. The secretary of state will have the power to "mandate" people to isolate if they do not isolate voluntarily. The government announced earlier today that localised lockdowns, ...

Elenoide the android was made to shake your hand. She looks like a Madame Tussad's rendition of a prim fifth-grade teacher. She's dressed in a salmon cardigan with scalloped edges, a knee-length striped skirt, and a wig made of ashy blonde human hair. Her hands are warmed by heating pads hidden beneath the palms. During experiments, she wears white butler gloves.

Only 38 per cent of people supported the UK government's change to coronavirus restrictions announced on 10 May, compared to 90 per cent of people who said they supported the lockdown measures announced on 23 March, according to a survey conducted by researchers at King's College London and Ipsos MORI. The measures brought in on 10 May largely affected England. They included a stronger emphasis on people going to work if they are unable to work from home, encouraging people to avoid public transport as much as possible, letting people exercise outside more than once a day and allowing people to meet up with one person from a household other than their own, providing the meeting takes place outside and at a distance of at least 2 metres. The poll, which surveyed 2254 people in the UK aged 16 to 75, was conducted between 20 and 22 May, before it emerged that prime ministerial aide Dominic Cummings drove more than 260 miles from home with his son and ill wife in March, at a time when the ...

The Traveling-Salesperson-Problem (TSP) is arguably one of the best-known NP-hard combinatorial optimization problems. The two sophisticated heuristic solvers LKH and EAX and respective (restart) variants manage to calculate close-to optimal or even optimal solutions, also for large instances with several thousand nodes in reasonable time. In this work we extend existing benchmarking studies by addressing anytime behaviour of inexact TSP solvers based on empirical runtime distributions leading to an increased understanding of solver behaviour and the respective relation to problem hardness. It turns out that performance ranking of solvers is highly dependent on the focused approximation quality. Insights on intersection points of performances offer huge potential for the construction of hybridized solvers depending on instance features. Moreover, instance features tailored to anytime performance and corresponding performance indicators will highly improve automated algorithm selection models by including comprehensive information on solver quality.