Autoregressive (AR) and Non-autoregressive (NAR) models have their own superiority on the performance and latency, combining them into one model may take advantage of both. Current combination frameworks focus more on the integration of multiple decoding paradigms with a unified generative model, e.g. Masked Language Model. However, the generalization can be harmful to the performance due to the gap between training objective and inference. In this paper, we aim to close the gap by preserving the original objective of AR and NAR under a unified framework. Specifically, we propose the Directional Transformer (Diformer) by jointly modelling AR and NAR into three generation directions (left-to-right, right-to-left and straight) with a newly introduced direction variable, which works by controlling the prediction of each token to have specific dependencies under that direction. The unification achieved by direction successfully preserves the original dependency assumption used in AR and NAR, retaining both generalization and performance. Experiments on 4 WMT benchmarks demonstrate that Diformer outperforms current united-modelling works with more than 1.5 BLEU points for both AR and NAR decoding, and is also competitive to the state-of-the-art independent AR and NAR models.

China is deploying machinegun-carrying robots to its western desert regions amid a standoff with India because troops are struggling with the high-altitude conditions, it has been claimed. Dozens of unmanned vehicles capable of carrying both weapons and supplies are being sent to Tibet, Indian media reports, with the majority deployed in border regions where Chinese troops are locked into a standoff with Indian soldiers. Vehicles include the Sharp Claw, which is mounted with a light machinegun and can be operated wirelessly, and the Mule-200, which is designed as an unmanned supply vehicle but can also be fitted with weapons. Beijing has sent 88 Sharp Claws to Tibet, which borders India high in the Himalayas, of which 38 are deployed to the border region, Times News Now has claimed. Some 120 Mule-200s have also been sent to Tibet, News Now reports, with a majority of them deployed to the border area.

Want to seem like the smartest member of your family these holidays? Why not brag about your vast knowledge of AI? It was a big year for artificial intelligence, so here's a round-up of Cosmos' AI favourites from 2021. A team of researchers from the University of Glasgow, UK, used machine learning algorithms to find future zoonotic (originating in animals) virus threats. According to the researchers, a major stumbling block for understanding zoonotic disease has been that scientists tend to prioritise well-known zoonotic virus families based on their common features.

In May 2021, Twitter, a platform notorious for abuse and hot-headedness, rolled out a "prompts" feature that suggests users think twice before sending a tweet. The following month, Facebook announced AI "conflict alerts" for groups, so that admins can take action where there may be "contentious or unhealthy conversations taking place." Amazon's Halo, launched in 2020, is a fitness band that monitors the tone of your voice. Wellness is no longer just the tracking of a heartbeat or the counting of steps, but the way we come across to those around us. Algorithmic therapeutic tools are being developed to predict and prevent negative behavior.

Electrical utilities depend on short-term demand forecasting to proactively adjust production and distribution in anticipation of major variations. This systematic review analyzes 240 works published in scholarly journals between 2000 and 2019 that focus on applying Artificial Intelligence (AI), statistical, and hybrid models to short-term load forecasting (STLF). This work represents the most comprehensive review of works on this subject to date. A complete analysis of the literature is conducted to identify the most popular and accurate techniques as well as existing gaps. The findings show that although Artificial Neural Networks (ANN) continue to be the most commonly used standalone technique, researchers have been exceedingly opting for hybrid combinations of different techniques to leverage the combined advantages of individual methods. The review demonstrates that it is commonly possible with these hybrid combinations to achieve prediction accuracy exceeding 99%. The most successful duration for short-term forecasting has been identified as prediction for a duration of one day at an hourly interval. The review has identified a deficiency in access to datasets needed for training of the models. A significant gap has been identified in researching regions other than Asia, Europe, North America, and Australia.

Modern software deployment process produces software that is uniform, and hence vulnerable to large-scale code-reuse attacks, such as Jump-Oriented Programming (JOP) attacks. Compiler-based diversification improves the resilience and security of software systems by automatically generating different assembly code versions of a given program. Existing techniques are efficient but do not have a precise control over the quality, such as the code size or speed, of the generated code variants.  This paper introduces Diversity by Construction (DivCon), a constraint-based compiler approach to software diversification. Unlike previous approaches, DivCon allows users to control and adjust the conflicting goals of diversity and code quality. A key enabler is the use of Large Neighborhood Search (LNS) to generate highly diverse assembly code efficiently. For larger problems, we propose a combination of LNS with a structural decomposition  of the problem. To further improve the diversification efficiency of DivCon against JOP attacks, we propose an application-specific distance measure tailored to the characteristics of JOP attacks.  We evaluate DivCon with 20 functions from a popular benchmark suite for embedded systems. These experiments show that DivCon's combination of LNS and our application-specific distance measure generates binary programs that are highly resilient against JOP  attacks (they share between 0.15% to 8% of JOP gadgets) with an optimality gap of 10%. Our results confirm that there is a trade-off between the quality of each assembly code version and the diversity of the entire pool of versions. In particular, the experiments  show that DivCon is able to generate binary programs that share a very small number of  gadgets, while delivering near-optimal code.  For constraint programming researchers and practitioners, this paper demonstrates that LNS is a valuable technique for finding diverse solutions. For security researchers and software  engineers, DivCon extends the scope of compiler-based diversification to performance-critical and resource-constrained applications.  

Recently emerged federated learning (FL) is an attractive distributed learning framework in which numerous wireless end-user devices can train a global model with the data remained autochthonous. Compared with the traditional machine learning framework that collects user data for centralized storage, which brings huge communication burden and concerns about data privacy, this approach can not only save the network bandwidth but also protect the data privacy. Despite the promising prospect, byzantine attack, an intractable threat in conventional distributed network, is discovered to be rather efficacious against FL as well. In this paper, we conduct a comprehensive investigation of the state-of-the-art strategies for defending against byzantine attacks in FL. We first provide a taxonomy for the existing defense solutions according to the techniques they used, followed by an across-the-board comparison and discussion. Then we propose a new byzantine attack method called weight attack to defeat those defense schemes, and conduct experiments to demonstrate its threat. The results show that existing defense solutions, although abundant, are still far from fully protecting FL. Finally, we indicate possible countermeasures for weight attack, and highlight several challenges and future research directions for mitigating byzantine attacks in FL.

Explainable artificial intelligence and interpretable machine learning are research fields growing in importance. Yet, the underlying concepts remain somewhat elusive and lack generally agreed definitions. While recent inspiration from social sciences has refocused the work on needs and expectations of human recipients, the field still misses a concrete conceptualisation. We take steps towards addressing this challenge by reviewing the philosophical and social foundations of human explainability, which we then translate into the technological realm. In particular, we scrutinise the notion of algorithmic black boxes and the spectrum of understanding determined by explanatory processes and explainees' background knowledge. This approach allows us to define explainability as (logical) reasoning applied to transparent insights (into black boxes) interpreted under certain background knowledge - a process that engenders understanding in explainees. We then employ this conceptualisation to revisit the much disputed trade-off between transparency and predictive power and its implications for ante-hoc and post-hoc explainers as well as fairness and accountability engendered by explainability. We furthermore discuss components of the machine learning workflow that may be in need of interpretability, building on a range of ideas from human-centred explainability, with a focus on explainees, contrastive statements and explanatory processes. Our discussion reconciles and complements current research to help better navigate open questions - rather than attempting to address any individual issue - thus laying a solid foundation for a grounded discussion and future progress of explainable artificial intelligence and interpretable machine learning. We conclude with a summary of our findings, revisiting the human-centred explanatory process needed to achieve the desired level of algorithmic transparency.

Nowadays Machine Learning (ML) techniques are extensively adopted in many socially sensitive systems, thus requiring to carefully study the fairness of the decisions taken by such systems. Many approaches have been proposed to address and to make sure there is no bias against individuals or specific groups which might originally come from biased training datasets or algorithm design. In this regard, we propose a fairness enforcing approach called EiFFFeL:Enforcing Fairness in Forests by Flipping Leaves which exploits tree-based or leaf-based post-processing strategies to relabel leaves of selected decision trees of a given forest. Experimental results show that our approach achieves a user defined group fairness degree without losing a significant amount of accuracy.

Artificial intelligence (AI) has had a profound impact on our society in recent years, but it's been around longer than you may realize. Many people attribute the beginning of AI to a paper written in 1950 by Alan Turing titled "Computer Machinery and Intelligence." The term artificial intelligence, however, was first coined in 1956 at a conference that took place at Dartmouth College in Hanover, New Hampshire. Since then, interest in AI has wavered. Its most recent resurgence can be attributed to IBM's Deep Blue chess-playing supercomputer and its question-answering machine Watson. Today, AI is part of our everyday lives – from facial recognition technology and ride-share apps to smart assistants.