Is this AI's worst prediction yet? Chris Sutton's guest this week, actor Éanna Hardwicke, plays Roy Keane in Saipan - a new film about the former Manchester United captain's infamous fallout with Republic of Ireland manager Mick McCarthy before the 2002 World Cup. It is in cinemas from Friday. Naturally, we asked AI who would play Sutton if a film were ever made about him. The best fit, apparently, is Hollywood heartthrob Tom Hardy - who is four inches shorter than BBC Sport football expert Sutton but is AI's top choice for the role because he is known for portraying tough, brooding characters with emotional depth. That just shows how way off the mark AI is, said Sutton. But I'm happy with Tom Hardy, even though he is not tall enough.

Explainable AI (XAI) methods often struggle to generate clear, interpretable outputs for users without domain expertise. We introduce Feature-Guided Neighbor Selection (FGNS), a post hoc method that enhances interpretability by selecting class-representative examples using both local and global feature importance. In a user study (N = 98) evaluating Kannada script classifications, FGNS significantly improved non-experts' ability to identify model errors while maintaining appropriate agreement with correct predictions. Participants made faster and more accurate decisions compared to those given traditional k-NN explanations. Quantitative analysis shows that FGNS selects neighbors that better reflect class characteristics rather than merely minimizing feature-space distance, leading to more consistent selection and tighter clustering around class prototypes. These results support FGNS as a step toward more human-aligned model assessment, although further work is needed to address the gap between explanation quality and perceived trust.

Recently, counterfactuals using "if-only" explanations have become very popular in eXplainable AI (XAI), as they describe which changes to feature-inputs of a black-box AI system result in changes to a (usually negative) decision-outcome. Even more recently, semi-factuals using "even-if" explanations have gained more attention. They elucidate the feature-input changes that do not change the decision-outcome of the AI system, with a potential to suggest more beneficial recourses. Some semi-factual methods use counterfactuals to the query-instance to guide semi-factual production (so-called counterfactual-guided methods), whereas others do not (so-called counterfactual-free methods). In this work, we perform comprehensive tests of 8 semi-factual methods on 7 datasets using 5 key metrics, to determine whether counterfactual guidance is necessary to find the best semi-factuals. The results of these tests suggests not, but rather that computing other aspects of the decision space lead to better semi-factual XAI.

Americans can now pre-order a'Smart Glock' that requires facial recognition and fingerprint technology to fire. Start-up firearms manufacturer Biofire is selling the futuristic-looking 9mm handgun for $1,500 with orders due to ship in 2024. The smart gun scans two forms of biometric ID, an optical fingerprint sensor and 3D infrared facial recognition, to ensure that only the gun's true owner can activate the firearm – cutting down on accidents and misused stolen weapons. The Broomfield, Colorado-based company hopes its pistol will put a dent in America's cycle of gun violence. More than 13,900 people have already been killed by guns in the U.S. in the first four months of 2023 alone, according to the nonprofit Gun Violence Archive.

"The study adds to a growing body of knowledge that the eye can be used as a window to the rest of the body," Pearse Keane, a researcher in ophthalmology and AI analysis not connected to the study, told The Verge. "Doctors have known for more than a hundred years that you could look in the eye and see signs of diabetes and high blood pressure. But the problem was manual assessment: the manual delineation of the vessels by human experts." The use of machine learning, says Keane, can overcome this challenge.

Recently, it has been proposed that fruitful synergies may exist between Deep Learning (DL) and Case Based Reasoning (CBR); that there are insights to be gained by applying CBR ideas to problems in DL (what could be called DeepCBR). In this paper, we report on a program of research that applies CBR solutions to the problem of Explainable AI (XAI) in the DL. We describe a series of twin-systems pairings of opaque DL models with transparent CBR models that allow the latter to explain the former using factual, counterfactual and semi-factual explanation strategies. This twinning shows that functional abstractions of DL (e.g., feature weights, feature importance and decision boundaries) can be used to drive these explanatory solutions. We also raise the prospect that this research also applies to the problem of Data Augmentation in DL, underscoring the fecundity of these DeepCBR ideas.

In recent years, there has been an explosion of AI research on counterfactual explanations as a solution to the problem of eXplainable AI (XAI). These explanations seem to offer technical, psychological and legal benefits over other explanation techniques. We survey 100 distinct counterfactual explanation methods reported in the literature. This survey addresses the extent to which these methods have been adequately evaluated, both psychologically and computationally, and quantifies the shortfalls occurring. For instance, only 21% of these methods have been user tested. Five key deficits in the evaluation of these methods are detailed and a roadmap, with standardised benchmark evaluations, is proposed to resolve the issues arising; issues, that currently effectively block scientific progress in this field.

The ability to apply artificial intelligence (AI) to ophthalmology is gathering pace, a consequence of remarkable collaboration between eye specialists and technologists whose forte is the ability to process vast amounts of data quickly. Irish ophthalmologist Dr Pearse Keane – based in Moorfields Hospital, London – has been the chief catalyst in developing AI software to detect 50 sight-threatening eye diseases. It operates by interpreting optical coherence tomography (OCT) scans of the back of the eye, which soon will be routine when going for an eye check. Automation in analysing scans for diseases such as wet age-related macular degeneration (AMD), the main cause of blindness in Europe, and diabetic retinopathy, is about to revolutionise patient outcomes with faster results affording earlier diagnosis and prompt treatment, and ultimately preventing avoidable sight loss. Since that initial breakthrough, the Keane team has developed an alert system for a third of people with AMD who later get it in their good eye and, potentially, an early-warning system for onset of neurodegenerative diseases, notably Alzheimer's.

Last week, at a conference in London, Dr Pearse Keane beamed an image onto the wall of an orange globe with a dark centre, encircled by red storms and a bright moon. It looked like a dying planet in a distant galaxy. In fact, it was a beautifully detailed scan of the back of a human eye, as awesome in its way as the night sky. These days, Dr Keane said, that single image betrays a lot of information. "We can now look at a retinal photograph and say: 'This is a woman.

"Eyes are the windows to the soul". It's probably many physicians' dreams to be able to tell what a patient has come down with by looking into their eyes. Researchers from the University College London (UCL) and Moorfields Eye Hospital are trying to realize this dream in a collaborative project called "AlzEye". By studying a database of eye scans which include details of patients' retina alongside with other vital health information, the research team hope to detect optical differences and see if they may be telltale signs of Alzheimer's disease. To facilitate the process, the team is engaging with Google DeepMind, to employ machine learning algorithms to go through scans and information of 300,000 patients aged 40 and above who had visited Moorfields between year 2008 and 2018.