It may be smart, but it's not that clever. Artificial intelligence is nothing without human input. The algorithms that drive AI rely on the expertise of programmers and it's still no more than a tool – albeit a powerful one – that scientists and engineers can use to solve problems. Yet this is not to say that AI isn't the fastest-growing deep technology in the world, with the potential to transform people's lives and boost nations' economies. Facilitating AI innovation has even become a priority for the UK government, as laid out in the National AI Strategy it published in September.

Distributional semantic models represent the meaning of words as vectors. We introduce a selection method to learn a vector space that each of its dimensions is a natural word. The selection method starts from the most frequent words and selects a subset, which has the best performance. The method produces a vector space that each of its dimensions is a word. This is the main advantage of the method compared to fusion methods such as NMF, and neural embedding models. We apply the method to the ukWaC corpus and train a vector space of N=1500 basis words. We report tests results on word similarity tasks for MEN, RG-65, SimLex-999, and WordSim353 gold datasets. Also, results show that reducing the number of basis vectors from 5000 to 1500 reduces accuracy by about 1.5-2%. So, we achieve good interpretability without a large penalty. Interpretability evaluation results indicate that the word vectors obtained by the proposed method using N=1500 are more interpretable than word embedding models, and the baseline method. We report the top 15 words of 1500 selected basis words in this paper.

This paper uses techniques from Random Matrix Theory to find the ideal training-testing data split for a simple linear regression with m data points, each an independent n-dimensional multivariate Gaussian. It defines "ideal" as satisfying the integrity metric, i.e. the empirical model error is the actual measurement noise, and thus fairly reflects the value or lack of same of the model. This paper is the first to solve for the training and test size for any model in a way that is truly optimal. The number of data points in the training set is the root of a quartic polynomial Theorem 1 derives which depends only on m and n; the covariance matrix of the multivariate Gaussian, the true model parameters, and the true measurement noise drop out of the calculations. The critical mathematical difficulties were realizing that the problems herein were discussed in the context of the Jacobi Ensemble, a probability distribution describing the eigenvalues of a known random matrix model, and evaluating a new integral in the style of Selberg and Aomoto. Mathematical results are supported with thorough computational evidence. This paper is a step towards automatic choices of training/test set sizes in machine learning.

Europe was the fastest growing region for machine learning hiring among tech industry companies in the three months ending October. The number of roles in Europe made up 9.4% of total machine learning jobs – up from 7.7% in the same quarter last year. That was followed by Middle East & Africa, which saw a -0.2 year-on-year percentage point change in machine learning roles. The figures are compiled by GlobalData, who track the number of new job postings from key companies in various sectors over time. Using textual analysis, these job advertisements are then classified thematically.

Christmas Spirit Foundation executive director Rick Dungey on bringing cheer to military families and how viewers can help. The top U.S. commander for the Middle East said Thursday that the United States will keep the current 2,500 troops in Iraq for the foreseeable future, and he warned that he expects increasing attacks on U.S. and Iraqi personnel by Iranian-backed militias determined to get American forces out. Marine Gen. Frank McKenzie said in an interview with The Associated Press at the Pentagon that despite the shift by U.S. forces to a non-combat role in Iraq, they will still provide air support and other military aid for Iraq's fight against the Islamic State. Noting that Iranian-backed militias want all Western forces out of Iraq, he said an ongoing uptick in violence may continue through December. Gen. McKenzie, commander of the United States Central Command, testifies before the House Armed Services Committee on the conclusion of military operations in Afghanistan and plans for future counterterrorism operations on Wednesday, Sept. 29, 2021, on Capitol Hill in Washington.

It is surrounded on all sides, regularly bombed, and plagued by shortages of vital medicines. Yet in the lead-up to Christmas, the isolated Gaza Strip has – for once – ample supplies of something the rest of the world craves but can rarely find: a brand new PlayStation 5. Sony's flagship video game console is hot property this holiday season, although most people who have asked for one will be sorely disappointed on Christmas morning. A global supply-chain crisis twinned with a shortage of semiconductors – vital computer chips used in the console – has kept stock scarce. While secondhand, resold and stolen PS5's can be found, they are rare and often cost much more than the £359-£449 retail price tag. In downtown Gaza City, the price is also way above the official figure.

Ethiopia's 13-month war has seen yet another dramatic turn as the federal government's counteroffensive against fighters from the northern Tigray region has made substantial advances, reversing the spectacular gains made recently by the Tigrayan forces in their push southwards. State media said this week the country's "joint gallant security forces" had retaken the strategic towns of Dessie and Kombolcha, the latest in a series of battleground victories since Prime Minister Abiy Ahmed said last month he would head to the front line and urged Ethiopians to join the fight. As fighting drags on, the government, with its tiny air force of 22 combat-capable aircraft, seems to have also realised that air power and timely intelligence can make all the difference in a conflict – especially one fought over vast and often mountainous areas like in Ethiopia's north. Although there has been no official confirmation, analysts have pointed to credible reports saying Ahmed's government has reached out in recent months to manufacturers of cheap and efficient armed drones hoping that air power will turn the tide in its way. Photographic evidence has pointed to the presence of Chinese Wing Loong 2 Unarmed Aerial Vehicles or UAVs at Ethiopian military bases, while a Bellingcat investigation in August found strong indications that Iranian armed drones, along with their ground control stations, had been spotted at Semera Airport.

Transformer-based models are not efficient in processing long sequences due to the quadratic space and time complexity of the self-attention modules. To address this limitation, Linformer and Informer are proposed to reduce the quadratic complexity to linear (modulo logarithmic factors) via low-dimensional projection and row selection respectively. These two models are intrinsically connected, and to understand their connection, we introduce a theoretical framework of matrix sketching. Based on the theoretical analysis, we propose Skeinformer to accelerate self-attention and further improve the accuracy of matrix approximation to self-attention with three carefully designed components: column sampling, adaptive row normalization and pilot sampling reutilization. Experiments on the Long Range Arena (LRA) benchmark demonstrate that our methods outperform alternatives with a consistently smaller time/space footprint.

Representation learners that disentangle factors of variation have already proven to be important in addressing various real world concerns such as fairness and interpretability. Initially consisting of unsupervised models with independence assumptions, more recently, weak supervision and correlated features have been explored, but without a causal view of the generative process. In contrast, we work under the regime of a causal generative process where generative factors are either independent or can be potentially confounded by a set of observed or unobserved confounders. We present an analysis of disentangled representations through the notion of disentangled causal process. We motivate the need for new metrics and datasets to study causal disentanglement and propose two evaluation metrics and a dataset. We show that our metrics capture the desiderata of disentangled causal process. Finally, we perform an empirical study on state of the art disentangled representation learners using our metrics and dataset to evaluate them from causal perspective.

Data-driven societal event forecasting methods exploit relevant historical information to predict future events. These methods rely on historical labeled data and cannot accurately predict events when data are limited or of poor quality. Studying causal effects between events goes beyond correlation analysis and can contribute to a more robust prediction of events. However, incorporating causality analysis in data-driven event forecasting is challenging due to several factors: (i) Events occur in a complex and dynamic social environment. Many unobserved variables, i.e., hidden confounders, affect both potential causes and outcomes. (ii) Given spatiotemporal non-independent and identically distributed (non-IID) data, modeling hidden confounders for accurate causal effect estimation is not trivial. In this work, we introduce a deep learning framework that integrates causal effect estimation into event forecasting. We first study the problem of Individual Treatment Effect (ITE) estimation from observational event data with spatiotemporal attributes and present a novel causal inference model to estimate ITEs. We then incorporate the learned event-related causal information into event prediction as prior knowledge. Two robust learning modules, including a feature reweighting module and an approximate constraint loss, are introduced to enable prior knowledge injection. We evaluate the proposed causal inference model on real-world event datasets and validate the effectiveness of proposed robust learning modules in event prediction by feeding learned causal information into different deep learning methods. Experimental results demonstrate the strengths of the proposed causal inference model for ITE estimation in societal events and showcase the beneficial properties of robust learning modules in societal event forecasting.