Artificial intelligence tools that seek to address complex public problems need to be developed with the input of the decision-makers who will implement them, Mitzi Bolton writes. Turn on the news, social media, or catch up with friends and you'll no doubt find conversations turning to the problems of society, things that could or should be done differently. Things the government ought to fix but seems unable to address. There's the risk of exceeding planetary boundaries, increased incidence of zoonotic diseases, climate change and its related impacts, continuing debates over management of the Murray Darling Basin, disincentives to workforce participation, handling of hotel quarantine, and many more. These and other highly challenging problems, often considered in isolation, come together when global progress on the Sustainable Development Goals (SDGs) is considered.

I could spend the remainder of our time on this concept of job roles for artificial intelligence; it's a favorite topic for me. I am a big proponent of the discipline of data science being a team sport. We currently have our engineers and our analysts and our operators. And the roles and disciplines around data science and data engineers have been morphing out of an additional duty on analysts and engineers into its own sub sector, its own discipline. We're looking at a cadre of data professionals that serve almost as a logistics function to our operators who are doing the mission-level analysis.

Banks and other financial firms are investing in "explainable" artificial intelligence that lets auditors and analysts trace how decisions about loans and other services are made by financial technologies, experts say. The increasing use of software with AI capabilities such as machine learning and data mining has automated banking operations, increasing efficiency and providing more services. But privacy and civil liberties groups contend that has come at a cost, with bias in the AI systems' algorithms leading to discrimination in the form of loans or other services denied based on sex or ethnicity. This perception of algorithmic bias is a big problem for banks, which are investing in technical solutions to solve the problem, Moutusi Sau, an analyst at research and advisory company Gartner Inc., told CQ Roll Call. That issue is known as the black box problem with AI systems: software decision-making processes that often are opaque to humans, making it difficult or impossible to determine how a decision was made.

Recent use of a satellite controlled weapons platform used in the killing of Iranian nuclear scientist, Mohsen Fakhrizadeh has invited international attention probably for the fact that a remotely controlled machine gun mounted on a pickup was used to pointedly kill him. It is for the first time that the machine gun was controlled remotely using advanced cameras and artificial intelligence and targeted only one individual without causing any collateral damage. Artificial intelligence-based platforms are the future of any battlefield. They can be easily deployed without being detected easily and cause havoc through enemy fire. They are stealthy and very effective. "The development of remote-controlled devices has seen phenomenal development since US forces started targeting terrorist networks with precise accuracy using the drones.

Joy Buolamwini from the MIT Media Lab says facial-recognition software has the highest error rates for darker-skinned females. New applications powered by artificial intelligence (AI) are being embraced by the public and private sectors. Their early uses hint at what's to come. In June 2020, IBM, Amazon and Microsoft announced that they were stepping back from facial-recognition software development amid concerns that it reinforces racial and gender bias. Amazon and Microsoft said they would stop selling facial-recognition software to police until new laws are passed in the United States to address potential human-rights abuses.

The continuing rise in the number of problems amenable to machine learning solutions, coupled with simultaneous growth in both computing power and variety of machine learning techniques has led to an explosion of interest in automated machine learning (AutoML). This paper presents Ensemble Squared (Ensemble$^2$), a "meta" AutoML system that ensembles at the level of AutoML systems. Ensemble$^2$ exploits the diversity of existing, competing AutoML systems by ensembling the top-performing models simultaneously generated by a set of them. Our work shows that diversity in AutoML systems is sufficient to justify ensembling at the AutoML system level. In demonstrating this, we also establish a new state of the art AutoML result on the OpenML classification challenge.

Governments are increasingly turning to algorithmic risk assessments when making important decisions, believing that these algorithms will improve public servants' ability to make policy-relevant predictions and thereby lead to more informed decisions. Yet because many policy decisions require balancing risk-minimization with competing social goals, evaluating the impacts of risk assessments requires considering how public servants are influenced by risk assessments when making policy decisions rather than just how accurately these algorithms make predictions. Through an online experiment with 2,140 lay participants simulating two high-stakes government contexts, we provide the first large-scale evidence that risk assessments can systematically alter decision-making processes by increasing the salience of risk as a factor in decisions and that these shifts could exacerbate racial disparities. These results demonstrate that improving human prediction accuracy with algorithms does not necessarily improve human decisions and highlight the need to experimentally test how government algorithms are used by human decision-makers.

Inductive Logic Programming (ILP) systems learn generalised, interpretable rules in a data-efficient manner utilising existing background knowledge. However, current ILP systems require training examples to be specified in a structured logical format. Neural networks learn from unstructured data, although their learned models may be difficult to interpret and are vulnerable to data perturbations at run-time. This paper introduces a hybrid neural-symbolic learning framework, called NSL, that learns interpretable rules from labelled unstructured data. NSL combines pre-trained neural networks for feature extraction with FastLAS, a state-of-the-art ILP system for rule learning under the answer set semantics. Features extracted by the neural components define the structured context of labelled examples and the confidence of the neural predictions determines the level of noise of the examples. Using the scoring function of FastLAS, NSL searches for short, interpretable rules that generalise over such noisy examples. We evaluate our framework on propositional and first-order classification tasks using the MNIST dataset as raw data. Specifically, we demonstrate that NSL is able to learn robust rules from perturbed MNIST data and achieve comparable or superior accuracy when compared to neural network and random forest baselines whilst being more general and interpretable.

Gaussian Processes (GPs) are a class of kernel methods that have shown to be very useful in geoscience applications. They are widely used because they are simple, flexible and provide very accurate estimates for nonlinear problems, especially in parameter retrieval. An addition to a predictive mean function, GPs come equipped with a useful property: the predictive variance function which provides confidence intervals for the predictions. The GP formulation usually assumes that there is no input noise in the training and testing points, only in the observations. However, this is often not the case in Earth observation problems where an accurate assessment of the instrument error is usually available. In this paper, we showcase how the derivative of a GP model can be used to provide an analytical error propagation formulation and we analyze the predictive variance and the propagated error terms in a temperature prediction problem from infrared sounding data.

Anomalous change detection (ACD) is an important problem in remote sensing image processing. Detecting not only pervasive but also anomalous or extreme changes has many applications for which methodologies are available. This paper introduces a nonlinear extension of a full family of anomalous change detectors. In particular, we focus on algorithms that utilize Gaussian and elliptically contoured (EC) distribution and extend them to their nonlinear counterparts based on the theory of reproducing kernels' Hilbert space. We illustrate the performance of the kernel methods introduced in both pervasive and ACD problems with real and simulated changes in multispectral and hyperspectral imagery with different resolutions (AVIRIS, Sentinel-2, WorldView-2, and Quickbird). A wide range of situations is studied in real examples, including droughts, wildfires, and urbanization. Excellent performance in terms of detection accuracy compared to linear formulations is achieved, resulting in improved detection accuracy and reduced false-alarm rates. Results also reveal that the EC assumption may be still valid in Hilbert spaces. We provide an implementation of the algorithms as well as a database of natural anomalous changes in real scenarios http://isp.uv.es/kacd.html.