In this paper, we present a study of a kernel-based consensual aggregation on randomly projected high-dimensional features of predictions for regression. The aggregation scheme is composed of two steps: the high-dimensional features of predictions, given by a large number of regression estimators, are randomly projected into a smaller subspace using Johnson-Lindenstrauss Lemma in the first step, and a kernel-based consensual aggregation is implemented on the projected features in the second step. We theoretically show that the performance of the aggregation scheme is close to the performance of the aggregation implemented on the original high-dimensional features, with high probability. Moreover, we numerically illustrate that the aggregation scheme upholds its performance on very large and highly correlated features of predictions given by different types of machines. The aggregation scheme allows us to flexibly merge a large number of redundant machines, plainly constructed without model selection or cross-validation. The efficiency of the proposed method is illustrated through several experiments evaluated on different types of synthetic and real datasets.

Developing artificial learning systems that can understand and generate natural language has been one of the long-standing goals of artificial intelligence. Recent decades have witnessed an impressive progress on both of these problems, giving rise to a new family of approaches. Especially, the advances in deep learning over the past couple of years have led to neural approaches to natural language generation (NLG). These methods combine generative language learning techniques with neural-networks based frameworks. With a wide range of applications in natural language processing, neural NLG (NNLG) is a new and fast growing field of research. In this state-of-the-art report, we investigate the recent developments and applications of NNLG in its full extent from a multidimensional view, covering critical perspectives such as multimodality, multilinguality, controllability and learning strategies. We summarize the fundamental building blocks of NNLG approaches from these aspects and provide detailed reviews of commonly used preprocessing steps and basic neural architectures. This report also focuses on the seminal applications of these NNLG models such as machine translation, description generation, automatic speech recognition, abstractive summarization, text simplification, question answering and generation, and dialogue generation. Finally, we conclude with a thorough discussion of the described frameworks by pointing out some open research directions.

The Final Report also makes specific recommendations for the introduction of legislation which regulates the use of facial recognition and other biometric technology, and for a moratorium on the use of this technology in AI-informed decision-making until such legislation is enacted. The recommendations of the AHRC have been submitted to the Australian Government. The Australian Government has the ability to determine whether to adopt the recommendations of the Report or not. The adoption of the AHRC's recommendations for the introduction of specific legislation governing the use of AI would signal a change in the approach to the regulation of AI and other emerging technologies that has been adopted in Australia to date. Free data access is an issue in the use of AI tools in the provision of legal services in Australia. The success of an AI tool will be determined by the size and diversity of the sample data which is used to train that tool. There are a number of factors that contribute to free data access in Australia and generally these factors apply across the spectrum of different categories of AI tools discussed in question 2 (being litigation, transactional and knowledge management tools).

Medical natural language processing (NLP) systems are a key enabling technology for transforming Big Data from clinical report repositories to information used to support disease models and validate intervention methods. However, current medical NLP systems fall considerably short when faced with the task of logically interpreting clinical text. In this paper, we describe a framework inspired by mechanisms of human cognition in an attempt to jump the NLP performance curve. The design centers about a hierarchical semantic compositional model (HSCM) which provides an internal substrate for guiding the interpretation process. The paper describes insights from four key cognitive aspects including semantic memory, semantic composition, semantic activation, and hierarchical predictive coding. We discuss the design of a generative semantic model and an associated semantic parser used to transform a free-text sentence into a logical representation of its meaning.

Purpose - To develop and validate a deep learning (DL) framework for the detection and quantification of drusen and reticular pseudodrusen (RPD) on optical coherence tomography scans. Design - Development and validation of deep learning models for classification and feature segmentation. Methods - A DL framework was developed consisting of a classification model and an out-of-distribution (OOD) detection model for the identification of ungradable scans; a classification model to identify scans with drusen or RPD; and an image segmentation model to independently segment lesions as RPD or drusen. Data were obtained from 1284 participants in the UK Biobank (UKBB) with a self-reported diagnosis of age-related macular degeneration (AMD) and 250 UKBB controls. Drusen and RPD were manually delineated by five retina specialists. The main outcome measures were sensitivity, specificity, area under the ROC curve (AUC), kappa, accuracy and intraclass correlation coefficient (ICC). Results - The classification models performed strongly at their respective tasks (0.95, 0.93, and 0.99 AUC, respectively, for the ungradable scans classifier, the OOD model, and the drusen and RPD classification model). The mean ICC for drusen and RPD area vs. graders was 0.74 and 0.61, respectively, compared with 0.69 and 0.68 for intergrader agreement. FROC curves showed that the model's sensitivity was close to human performance. Conclusions - The models achieved high classification and segmentation performance, similar to human performance. Application of this robust framework will further our understanding of RPD as a separate entity from drusen in both research and clinical settings.

For many centuries, the goal of linguistics has been to capture this capacity by a formal description--a grammar--consisting of a systematic set of rules and/or principles that determine which sentences are part of a given language and which are not (Bod, 2013). Over the years, these formal grammars have taken many forms but common to them all is the assumption that they capture the idealized linguistic competence of a native speaker/hearer, independent of any memory limitations or other non-linguistic cognitive constraints (Chomsky, 1965; Miller, 2000). These abstract formal descriptions have come to play a foundational role in the language sciences, from linguistics, psycholinguistics, and neurolinguistics (Hauser et al., 2002; Pinker, 2003) to computer science, engineering, and machine learning (Klein and Manning, 2003; Dyer et al., 2016; Gómez-Rodríguez et al., 2018). Despite evidence that processing difficulty underpins the unacceptability of certain sentences (Morrill, 2010; Hawkins, 2004), the cognitive independence assumption that is a defining feature of linguistic competence has not been examined in a systematic way using the tools of formal grammar. It is therefore unclear whether these supposedly idealized descriptions of language are free of non-linguistic cognitive constraints, such as memory limitations.

Stochastic latent variable models (LVMs) achieve state-of-the-art performance on natural image generation but are still inferior to deterministic models on speech. In this paper, we develop a speech benchmark of popular temporal LVMs and compare them against state-of-the-art deterministic models. We report the likelihood, which is a much used metric in the image domain, but rarely, or incomparably, reported for speech models. To assess the quality of the learned representations, we also compare their usefulness for phoneme recognition. Finally, we adapt the Clockwork VAE, a state-of-the-art temporal LVM for video generation, to the speech domain. Despite being autoregressive only in latent space, we find that the Clockwork VAE can outperform previous LVMs and reduce the gap to deterministic models by using a hierarchy of latent variables.

Two centuries after Charles Darwin put the theory forward, a new study finally shows that birds living near the equator are more colourful. Scientists have used artificial intelligence (AI) to identify the amount of colour in photos of over 24,000 preserved birds from the Natural History Museum's collection. Tropical birds living near the equator are roughly 30 per cent more colourful than non-tropical birds living nearer the poles, the scientists found, but they don't know exactly why. The long-held theory, first suspected by Charles Darwin and other naturalists in the 18th and 19th centuries, hasn't been proven until now, the experts say. Research from the University of Sheffield found tropical birds living near the equator are roughly 30 per cent more colourful than non-tropical birds living nearer the poles.

Alphabet's Wing division has announced that it's launching a drone delivery service in the Dallas-Fort Worth (DFW) metroplex on April 7th. "With this service, the DFW area will be the largest metro in the world, and the first in the United States, with access to on-demand drone delivery," a company spokesperson said in an emailed statement. Wing's primary launch customer is Walgreens, which will deliver health and wellness products directly to customer's homes. For that, it will use a new operational model where drones are staged at one of its own store parking lots, rather than a Wing facility. It will also be delivering ice cream from Blue Bell Creameries, Easyvet prescription pet medications (yep) and first aid kits from Texas Health.

A team member using a 3D imaging system to take images of stink bugs from many angles to train the AI model inside the app. This requires several hundred images per species. Australia's national science agency, CSIRO, is using artificial intelligence (AI) to develop an app that will help keep brown marmorated stink bugs out of Australia, an invasive species with the potential to wipe out more than 300 different species of plants if it made it past quarantine. The app, being developed for the Department of Agriculture, Water and the Environment (DAWE), is based on a prototype co-funded by Microsoft to identify seeds of noxious weedy daisies, using AI to identify stink bug species based on thousands of specimens held in CSIRO's National Research Collections Australia. DAWE is now trialling the app in its quarantine stations.