Today, many systems use artificial intelligence (AI) to solve complex problems. While this often increases system effectiveness, developing a production-ready AI-based system is a difficult task. Thus, solid AI engineering practices are required to ensure the quality of the resulting system and to improve the development process. While several practices have already been proposed for the development of AI-based systems, detailed practical experiences of applying these practices are rare. In this paper, we aim to address this gap by collecting such experiences during a case study, namely the development of an autonomous stock trading system that uses machine learning functionality to invest in stocks. We selected 10 AI engineering practices from the literature and systematically applied them during development, with the goal to collect evidence about their applicability and effectiveness. Using structured field notes, we documented our experiences. Furthermore, we also used field notes to document challenges that occurred during the development, and the solutions we applied to overcome them. Afterwards, we analyzed the collected field notes, and evaluated how each practice improved the development. Lastly, we compared our evidence with existing literature. Most applied practices improved our system, albeit to varying extent, and we were able to overcome all major challenges. The qualitative results provide detailed accounts about 10 AI engineering practices, as well as challenges and solutions associated with such a project. Our experiences therefore enrich the emerging body of evidence in this field, which may be especially helpful for practitioner teams new to AI engineering.
相關內容
This paper presents a novel RL algorithm, S-REINFORCE, which is designed to generate interpretable policies for dynamic decision-making tasks. The proposed algorithm leverages two types of function approximators, namely Neural Network (NN) and Symbolic Regressor (SR), to produce numerical and symbolic policies, respectively. The NN component learns to generate a numerical probability distribution over the possible actions using a policy gradient, while the SR component captures the functional form that relates the associated states with the action probabilities. The SR-generated policy expressions are then utilized through importance sampling to improve the rewards received during the learning process. We have tested the proposed S-REINFORCE algorithm on various dynamic decision-making problems with low and high dimensional action spaces, and the results demonstrate its effectiveness and impact in achieving interpretable solutions. By leveraging the strengths of both NN and SR, S-REINFORCE produces policies that are not only well-performing but also easy to interpret, making it an ideal choice for real-world applications where transparency and causality are crucial.
Estimating the pose of an uncooperative spacecraft is an important computer vision problem for enabling the deployment of automatic vision-based systems in orbit, with applications ranging from on-orbit servicing to space debris removal. Following the general trend in computer vision, more and more works have been focusing on leveraging Deep Learning (DL) methods to address this problem. However and despite promising research-stage results, major challenges preventing the use of such methods in real-life missions still stand in the way. In particular, the deployment of such computation-intensive algorithms is still under-investigated, while the performance drop when training on synthetic and testing on real images remains to mitigate. The primary goal of this survey is to describe the current DL-based methods for spacecraft pose estimation in a comprehensive manner. The secondary goal is to help define the limitations towards the effective deployment of DL-based spacecraft pose estimation solutions for reliable autonomous vision-based applications. To this end, the survey first summarises the existing algorithms according to two approaches: hybrid modular pipelines and direct end-to-end regression methods. A comparison of algorithms is presented not only in terms of pose accuracy but also with a focus on network architectures and models' sizes keeping potential deployment in mind. Then, current monocular spacecraft pose estimation datasets used to train and test these methods are discussed. The data generation methods: simulators and testbeds, the domain gap and the performance drop between synthetically generated and lab/space collected images and the potential solutions are also discussed. Finally, the paper presents open research questions and future directions in the field, drawing parallels with other computer vision applications.
Deadlocks are one of the most notorious concurrency bugs, and significant research has focused on detecting them efficiently. Dynamic predictive analyses work by observing concurrent executions, and reason about alternative interleavings that can witness concurrency bugs. Such techniques offer scalability and sound bug reports, and have emerged as an effective approach for concurrency bug detection, such as data races. Effective dynamic deadlock prediction, however, has proven a challenging task, as no deadlock predictor currently meets the requirements of soundness, high-precision, and efficiency. In this paper, we first formally establish that this tradeoff is unavoidable, by showing that (a) sound and complete deadlock prediction is intractable, in general, and (b) even the seemingly simpler task of determining the presence of potential deadlocks, which often serve as unsound witnesses for actual predictable deadlocks, is intractable. The main contribution of this work is a new class of predictable deadlocks, called sync(hronization)-preserving deadlocks. Informally, these are deadlocks that can be predicted by reordering the observed execution while preserving the relative order of conflicting critical sections. We present two algorithms for sound deadlock prediction based on this notion. Our first algorithm SPDOffline detects all sync-preserving deadlocks, with running time that is linear per abstract deadlock pattern, a novel notion also introduced in this work. Our second algorithm SPDOnline predicts all sync-preserving deadlocks that involve two threads in a strictly online fashion, runs in overall linear time, and is better suited for a runtime monitoring setting. We implemented both our algorithms and evaluated their ability to perform offline and online deadlock-prediction on a large dataset of standard benchmarks.
A number of leading AI companies, including OpenAI, Google DeepMind, and Anthropic, have the stated goal of building artificial general intelligence (AGI) - AI systems that achieve or exceed human performance across a wide range of cognitive tasks. In pursuing this goal, they may develop and deploy AI systems that pose particularly significant risks. While they have already taken some measures to mitigate these risks, best practices have not yet emerged. To support the identification of best practices, we sent a survey to 92 leading experts from AGI labs, academia, and civil society and received 51 responses. Participants were asked how much they agreed with 50 statements about what AGI labs should do. Our main finding is that participants, on average, agreed with all of them. Many statements received extremely high levels of agreement. For example, 98% of respondents somewhat or strongly agreed that AGI labs should conduct pre-deployment risk assessments, dangerous capabilities evaluations, third-party model audits, safety restrictions on model usage, and red teaming. Ultimately, our list of statements may serve as a helpful foundation for efforts to develop best practices, standards, and regulations for AGI labs.
We develop the first active learning method in the predict-then-optimize framework. Specifically, we develop a learning method that sequentially decides whether to request the "labels" of feature samples from an unlabeled data stream, where the labels correspond to the parameters of an optimization model for decision-making. Our active learning method is the first to be directly informed by the decision error induced by the predicted parameters, which is referred to as the Smart Predict-then-Optimize (SPO) loss. Motivated by the structure of the SPO loss, our algorithm adopts a margin-based criterion utilizing the concept of distance to degeneracy and minimizes a tractable surrogate of the SPO loss on the collected data. In particular, we develop an efficient active learning algorithm with both hard and soft rejection variants, each with theoretical excess risk (i.e., generalization) guarantees. We further derive bounds on the label complexity, which refers to the number of samples whose labels are acquired to achieve a desired small level of SPO risk. Under some natural low-noise conditions, we show that these bounds can be better than the naive supervised learning approach that labels all samples. Furthermore, when using the SPO+ loss function, a specialized surrogate of the SPO loss, we derive a significantly smaller label complexity under separability conditions. We also present numerical evidence showing the practical value of our proposed algorithms in the settings of personalized pricing and the shortest path problem.
As a consequence of the increasing influence of machine learning on our lives, everyone needs competencies to understand corresponding phenomena, but also to get involved in shaping our world and making informed decisions regarding the influences on our society. Therefore, in K-12 education, students need to learn about core ideas and principles of machine learning. However, for this target group, achieving all of the aforementioned goals presents an enormous challenge. To this end, we present a teaching concept that combines a playful and accessible unplugged approach focusing on conceptual understanding with empowering students to actively apply machine learning methods and reflect their influence on society, building upon decision tree learning.
We present CEMA: Causal Explanations for Multi-Agent decision-making; a system to generate causal explanations for agents' decisions in stochastic sequential multi-agent environments. The core of CEMA is a novel causal selection method which, unlike prior work that assumes a specific causal structure, is applicable whenever a probabilistic model for predicting future states of the environment is available. We sample counterfactual worlds with this model which are used to identify and rank the salient causes behind decisions. We also designed CEMA to meet the requirements of social explainable AI. It can generate contrastive explanations based on selected causes and it works as an interaction loop with users to assure relevance and intelligibility for them. We implement CEMA for motion planning for autonomous driving and test it in four diverse simulated scenarios. We show that CEMA correctly and robustly identifies the relevant causes behind decisions and delivers relevant explanations to users' queries.
Knowledge graph embedding (KGE) is a increasingly popular technique that aims to represent entities and relations of knowledge graphs into low-dimensional semantic spaces for a wide spectrum of applications such as link prediction, knowledge reasoning and knowledge completion. In this paper, we provide a systematic review of existing KGE techniques based on representation spaces. Particularly, we build a fine-grained classification to categorise the models based on three mathematical perspectives of the representation spaces: (1) Algebraic perspective, (2) Geometric perspective, and (3) Analytical perspective. We introduce the rigorous definitions of fundamental mathematical spaces before diving into KGE models and their mathematical properties. We further discuss different KGE methods over the three categories, as well as summarise how spatial advantages work over different embedding needs. By collating the experimental results from downstream tasks, we also explore the advantages of mathematical space in different scenarios and the reasons behind them. We further state some promising research directions from a representation space perspective, with which we hope to inspire researchers to design their KGE models as well as their related applications with more consideration of their mathematical space properties.
Fast developing artificial intelligence (AI) technology has enabled various applied systems deployed in the real world, impacting people's everyday lives. However, many current AI systems were found vulnerable to imperceptible attacks, biased against underrepresented groups, lacking in user privacy protection, etc., which not only degrades user experience but erodes the society's trust in all AI systems. In this review, we strive to provide AI practitioners a comprehensive guide towards building trustworthy AI systems. We first introduce the theoretical framework of important aspects of AI trustworthiness, including robustness, generalization, explainability, transparency, reproducibility, fairness, privacy preservation, alignment with human values, and accountability. We then survey leading approaches in these aspects in the industry. To unify the current fragmented approaches towards trustworthy AI, we propose a systematic approach that considers the entire lifecycle of AI systems, ranging from data acquisition to model development, to development and deployment, finally to continuous monitoring and governance. In this framework, we offer concrete action items to practitioners and societal stakeholders (e.g., researchers and regulators) to improve AI trustworthiness. Finally, we identify key opportunities and challenges in the future development of trustworthy AI systems, where we identify the need for paradigm shift towards comprehensive trustworthy AI systems.
Graphical causal inference as pioneered by Judea Pearl arose from research on artificial intelligence (AI), and for a long time had little connection to the field of machine learning. This article discusses where links have been and should be established, introducing key concepts along the way. It argues that the hard open problems of machine learning and AI are intrinsically related to causality, and explains how the field is beginning to understand them.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191