Ai Magazine最新文献

This article provides a somewhat whimsical discussion of the impact that AI, or “robots”, will have on the future of education. Interwoven with numerous references to science fiction, and at least one to Alice Cooper, is a very serious consideration of the manner in which AI may completely redefine the way we learn and grow as humans. From Holistic Assessment of Learning (HAL) to a Yoda on Yer Shoulda, a future of life-embedding learning is described.

This study investigates the dynamic landscape of governance frameworks for emerging technologies, particularly artificial intelligence (AI), within the context of public policy in expanded BRICS nations (Brazil, Russia, India, China, South Africa, Egypt, Ethiopia, Iran, and the United Arab Emirates). Understanding the ethical implications and crafting policy tools to guide the development and deployment of AI is crucial. Analyzing findings from AI policy initiatives, this research delves into managing new technologies, emphasizing the evolving discourse on AI ethics. It stresses the importance of embedding ethical considerations into governance frameworks to address societal concerns and foster responsible AI advancement. Additionally, strong legal frameworks are essential, striking a balance between fostering innovation and ensuring accountability, thereby enhancing confidence and transparency in AI systems. This study underscores the significance of public policy in shaping AI governance, advocating for inclusive, participatory approaches involving stakeholders from diverse sectors. Adaptive governance frameworks capable of navigating the evolving AI landscape and its societal ramifications are emphasized. A holistic governance strategy based on insights from AI policy is recommended, aiming to reconcile innovation with ethical, legal, and societal considerations. Policymakers are urged to foster stakeholder engagement, ensuring that AI advancements benefit society while upholding ethical, just, and accountable standards.

This paper explores the rapidly evolving ecosystem of publicly available AI models and their potential implications on the security and safety landscape. Understanding their potential risks and vulnerabilities is crucial as AI models become increasingly prevalent. We review the current security and safety scenarios while highlighting challenges such as tracking issues, remediation, and the absence of AI model lifecycle and ownership processes. Comprehensive strategies to enhance security and safety for both model developers and end-users are proposed. This paper provides several foundational pieces for more standardized security, safety, and transparency in developing and operating generative AI models and the larger open ecosystems and communities forming around them.

In the rapidly evolving fields of artificial intelligence (AI) and machine learning (ML), the reproducibility crisis underscores the urgent need for clear validation methodologies to maintain scientific integrity and encourage advancement. The crisis is compounded by the prevalent confusion over validation terminology. In response to this challenge, we introduce a framework that clarifies the roles and definitions of key validation efforts: repeatability, dependent and independent reproducibility, and direct and conceptual replicability. This structured framework aims to provide AI/ML researchers with the necessary clarity on these essential concepts, facilitating the appropriate design, conduct, and interpretation of validation studies. By articulating the nuances and specific roles of each type of validation study, we aim to enhance the reliability and trustworthiness of research findings and support the community's efforts to address reproducibility challenges effectively.

Meaningful progress has been made in open world learning (OWL), enhancing the ability of agents to detect, characterize, and incrementally learn novelty in dynamic environments. However, novelty remains a persistent challenge for agents relying on state-of-the-art learning algorithms. This article considers the current state of OWL, drawing on insights from a recent DARPA research program on this topic. We identify open issues that impede further advancements spanning theory, design, and evaluation. In particular, we emphasize the challenges posed by dynamic scenarios that are crucial to understand for ensuring the viability of agents designed for real-world environments. The article provides suggestions for setting a new research agenda that effectively addresses these open issues.

Many research fields are currently reckoning with issues of poor levels of reproducibility. Some label it a “crisis,” and research employing or building machine learning (ML) models is no exception. Issues including lack of transparency, data or code, poor adherence to standards, and the sensitivity of ML training conditions mean that many papers are not even reproducible in principle. Where they are, though, reproducibility experiments have found worryingly low degrees of similarity with original results. Despite previous appeals from ML researchers on this topic and various initiatives from conference reproducibility tracks to the ACM's new Emerging Interest Group on Reproducibility and Replicability, we contend that the general community continues to take this issue too lightly. Poor reproducibility threatens trust in and integrity of research results. Therefore, in this article, we lay out a new perspective on the key barriers and drivers (both procedural and technical) to increased reproducibility at various levels (methods, code, data, and experiments). We then map the drivers to the barriers to give concrete advice for strategies for researchers to mitigate reproducibility issues in their own work, to lay out key areas where further research is needed in specific areas, and to further ignite discussion on the threat presented by these urgent issues.

Despite an extensive body of literature on trust in technology, designing trustworthy AI systems for high-stakes decision domains remains a significant challenge. Widely used system design guidelines and tools are rarely attuned to domain-specific trustworthiness principles. In this study, we introduce a design framework to address this gap within intelligence analytic tasks, called the Principles-based Approach for Designing Trustworthy, Human-centered AI using the MAST Methodology (PADTHAI-MM). PADTHAI-MM builds on the Multisource AI Scorecard Table (MAST), an AI decision support system evaluation tool designed in accordance to the U.S. Intelligence Community's standards for system trustworthiness. We demonstrate PADTHAI-MM in our development of the Reporting Assistant for Defense and Intelligence Tasks (READIT), a research platform that leverages data visualizations and natural language processing-based text analysis to emulate AI-enabled intelligence reporting aids. To empirically assess the efficacy of PADTHAI-MM, we developed two versions of READIT for comparison: a “High-MAST” version, which incorporates AI contextual information and explanations, and a “Low-MAST” version, designed to be akin to inscrutable “black box” AI systems. Through an iterative design process guided by stakeholder feedback, our multidisciplinary design team developed prototypes that were evaluated by experienced intelligence analysts. Results substantially supported the viability of PADTHAI-MM in designing for system trustworthiness in this task domain. We also explored the relationship between analysts' MAST ratings and three theoretical categories of information known to impact trust: process, purpose, and performance. Overall, our study supports the practical and theoretical viability of PADTHAI-MM as an approach to designing trustable AI systems.

Today's robots do not yet learn the general skills that are necessary to provide home care, to be nursing assistants, to interact with people, or do household chores nearly as well as people do. Addressing the aspirational goal of creating service robots requires improving how they are created. Today's mainstream AIs are not created by agents learning from experiences doing tasks in real-world contexts and interacting with people. Today's robots do not learn by sensing, acting, doing experiments, and collaborating. Future robots will need to learn from such experiences in order to be ready for robust deployment in human service applications. This paper investigates what aspirational future autonomous human-compatible service robots will need to know. It recommends developing experiential (robotic) foundation models (FMs) for bootstrapping them.

The growing importance of understanding and addressing algorithmic bias in artificial intelligence (AI) has led to a surge in research on AI fairness, which often assumes that the underlying data are independent and identically distributed (IID). However, real-world data frequently exist in non-IID graph structures that capture connections among individual units. To effectively mitigate bias in AI systems, it is essential to bridge the gap between traditional fairness literature, designed for IID data, and the prevalence of non-IID graph data. This survey reviews recent advancements in fairness amidst non-IID graph data, including the newly introduced fair graph generation and the commonly studied fair graph classification. In addition, available datasets and evaluation metrics for future research are identified, the limitations of existing work are highlighted, and promising future directions are proposed.

The brute-force scaleup of training datasets, learnable parameters and computation power, has become a prevalent strategy for developing more robust learning models. However, due to bottlenecks in data, computation, and trust, the sustainability of this strategy is a serious concern. In this paper, we attempt to address this issue in a parsimonious manner (i.e., achieving greater potential with simpler models). The key is to drive models using domain-specific knowledge, such as symbols, logic, and formulas, instead of purely relying on scaleup. This approach allows us to build a framework that uses this knowledge as “building blocks” to achieve parsimony in model design, training, and interpretation. Empirical results show that our methods surpass those that typically follow the scaling law. We also demonstrate our framework in AI for science, specifically in the problem of drug-drug interaction prediction. We hope our research can foster more diverse technical roadmaps in the era of foundation models.