This paper introduces an open source platform to support the rapid development of computer vision applications at scale. The platform puts the efficient data development at the center of the machine learning development process, integrates active learning methods, data and model version control, and uses concepts such as projects to enable fast iterations of multiple task specific datasets in parallel. This platform abstracts the development process into core states and operations, and integrates third party tools via open APIs as implementations of the operations. This open design reduces the development cost and adoption cost for ML teams with existing tools. At the same time, the platform supports recording project development histories, through which successful projects can be shared to further boost model production efficiency on similar tasks. The platform is open source and is already used internally to meet the increasing demand for different real world computer vision applications.

What is learned by sophisticated neural network agents such as AlphaZero? This question is of both scientific and practical interest. If the representations of strong neural networks bear no resemblance to human concepts, our ability to understand faithful explanations of their decisions will be restricted, ultimately limiting what we can achieve with neural network interpretability. In this work we provide evidence that human knowledge is acquired by the AlphaZero neural network as it trains on the game of chess. By probing for a broad range of human chess concepts we show when and where these concepts are represented in the AlphaZero network. We also provide a behavioural analysis focusing on opening play, including qualitative analysis from chess Grandmaster Vladimir Kramnik. Finally, we carry out a preliminary investigation looking at the low-level details of AlphaZero's representations, and make the resulting behavioural and representational analyses available online.

Explainable artificial intelligence (XAI) and interpretable machine learning (IML) have become active research fields in recent years (Adadi and Berrada 2018; Molnar 2019). This is a natural consequence as complex machine learning (ML) models are now applied to solve supervised learning problems in many high-risk areas: cancer prognosis (Kourou et al. 2015), credit scoring (Kvamme et al. 2018), and money laundering detection (Jullum, Løland, et al. 2020). The high prediction accuracy of complex ML models often comes at the expense of model interpretability. As the goal of science is to gain knowledge from the collected data, the use of black-box models hinders the understanding of the underlying relationship between the features and the response, and thereby curtail scientific discovery. Model explanation frameworks from the XAI field extract the hidden knowledge about the underlying data structure captured by a black-box model, and thereby make the model's decision-making process transparent. This is crucial for, e.g., medical researchers that apply an ML model to obtain well-performing predictions, but who simultaneously also strive to discover important risk factors. Another driving factor is the Right to Explanation legislation in EU's General Data Protection Regulation (GDPR) (European Commission 2016).

There is a tendency across different subfields in AI to valorize a small collection of influential benchmarks. These benchmarks operate as stand-ins for a range of anointed common problems that are frequently framed as foundational milestones on the path towards flexible and generalizable AI systems. State-of-the-art performance on these benchmarks is widely understood as indicative of progress towards these long-term goals. In this position paper, we explore the limits of such benchmarks in order to reveal the construct validity issues in their framing as the functionally "general" broad measures of progress they are set up to be.

Do language models have beliefs about the world? Dennett (1995) famously argues that even thermostats have beliefs, on the view that a belief is simply an informational state decoupled from any motivational state. In this paper, we discuss approaches to detecting when models have beliefs about the world, and we improve on methods for updating model beliefs to be more truthful, with a focus on methods based on learned optimizers or hypernetworks. Our main contributions include: (1) new metrics for evaluating belief-updating methods that focus on the logical consistency of beliefs, (2) a training objective for Sequential, Local, and Generalizing model updates (SLAG) that improves the performance of learned optimizers, and (3) the introduction of the belief graph, which is a new form of interface with language models that shows the interdependencies between model beliefs. Our experiments suggest that models possess belief-like qualities to only a limited extent, but update methods can both fix incorrect model beliefs and greatly improve their consistency. Although off-the-shelf optimizers are surprisingly strong belief-updating baselines, our learned optimizers can outperform them in more difficult settings than have been considered in past work. Code is available at https://github.com/peterbhase/SLAG-Belief-Updating

This paper presents a new task of predicting the coverage of a text document for relation extraction (RE): does the document contain many relational tuples for a given entity? Coverage predictions are useful in selecting the best documents for knowledge base construction with large input corpora. To study this problem, we present a dataset of 31,366 diverse documents for 520 entities. We analyze the correlation of document coverage with features like length, entity mention frequency, Alexa rank, language complexity and information retrieval scores. Each of these features has only moderate predictive power. We employ methods combining features with statistical models like TF-IDF and language models like BERT. The model combining features and BERT, HERB, achieves an F1 score of up to 46%. We demonstrate the utility of coverage predictions on two use cases: KB construction and claim refutation.

The metaverse, enormous virtual-physical cyberspace, has brought unprecedented opportunities for artists to blend every corner of our physical surroundings with digital creativity. This article conducts a comprehensive survey on computational arts, in which seven critical topics are relevant to the metaverse, describing novel artworks in blended virtual-physical realities. The topics first cover the building elements for the metaverse, e.g., virtual scenes and characters, auditory, textual elements. Next, several remarkable types of novel creations in the expanded horizons of metaverse cyberspace have been reflected, such as immersive arts, robotic arts, and other user-centric approaches fuelling contemporary creative outputs. Finally, we propose several research agendas: democratising computational arts, digital privacy, and safety for metaverse artists, ownership recognition for digital artworks, technological challenges, and so on. The survey also serves as introductory material for artists and metaverse technologists to begin creations in the realm of surrealistic cyberspace.

High annotation costs are a substantial bottleneck in applying modern deep learning architectures to clinically relevant medical use cases, substantiating the need for novel algorithms to learn from unlabeled data. In this work, we propose ContIG, a self-supervised method that can learn from large datasets of unlabeled medical images and genetic data. Our approach aligns images and several genetic modalities in the feature space using a contrastive loss. We design our method to integrate multiple modalities of each individual person in the same model end-to-end, even when the available modalities vary across individuals. Our procedure outperforms state-of-the-art self-supervised methods on all evaluated downstream benchmark tasks. We also adapt gradient-based explainability algorithms to better understand the learned cross-modal associations between the images and genetic modalities. Finally, we perform genome-wide association studies on the features learned by our models, uncovering interesting relationships between images and genetic data.

Revenue NSW's former Chief Digital Office Kathleen Mackay has picked up the top gong in this year's CIO50 Australia, becoming the first woman to take out the country's premier award for senior technology and digital executives. Revenue NSW Deputy Secretary Scott Johnston said Kathleen's leadership was instrumental in enabling innovation in an environment where agility and risk taking were sometimes overlooked. She led by example and showed her peers how new ways of working could deliver positive outcomes for customers and Revenue NSW," Mr Johnston said. "She championed the use of artificial intelligence coupled with advanced analytics to identify vulnerable customers early and to better target fines enforcement action. "The program diverts vulnerable customers away from the collections process and offers an alternative way to resolve debts. "Kathleen took process automation from idea to reality and supported the team to implement significant changes across Revenue NSW.

A new research tool launched by buyer's agency network BuyersBuyers promises to take the guesswork out of suburb selection by using artificial intelligence to match a purchaser's budget with their best prospects for capital growth. BuyersBuyers co-founder Pete Wargent said the unique Where to Buy tool provided answers on which location and what sort of property would be the best choice for investors or owner-occupiers under a specific budget. "We've created a simple online process that improves the customer journey, and can help buyers to reduce time, cost and stress in their search," Mr Wargent said. The tool, which was developed in collaboration with RiskWise Property Research, assesses metrics including housing supply, median values, 12-month price growth and vacancy rates to determine whether the locations would provide risky or rewarding prospects for investment. RiskWise Property Research chief executive Doron Peleg said the new offering would complement a suite of research tools developed in conjunction with BuyersBuyers that were free for subscribers. "For example, for 2022, we ran a list of thirty suburbs which are expected to perform well for investors with a budget of up to around $1 million," Mr Peleg said.