Proceedings of the AAAI Symposium Series最新文献

{"title":"AI Health Agents: Pathway2vec, ReflectE, Category Theory, and Longevity","authors":"Melanie Swan, Takashi Kido, Eric Roland, Renato P. Dos Santos","doi":"10.1609/aaaiss.v3i1.31249","DOIUrl":"https://doi.org/10.1609/aaaiss.v3i1.31249","url":null,"abstract":"Health Agents are introduced as the concept of a personalized AI health advisor overlay for continuous health monitoring (e.g. 1000x/minute) medical-grade smartwatches and wearables for “healthcare by app” instead of “sickcare by appointment.” Individuals can customize the level of detail in the information they view. Health Agents “speak” natural language to humans and formal language to the computational infrastructure, possibly outputting the mathematics of personalized homeostatic health as part of their reinforcement learning agent behavior. As an AI health interface, the agent facilitates the management of precision medicine as a service. Healthy longevity is a high-profile area characterized by the increasing acceptance of medical intervention, longevity biotech venture capital investment, and global priority as 2 billion people will be over 65 in 2050. Aging hallmarks, biomarkers, and clocks provide a quantitative measure for intervention. Some of the leading interventions include metformin, rapamycin, spermidine, NAD+/sirtuins, alpha-ketoglutarate, and taurine. AI-driven digital biology, longevity medicine, and Web3 personalized healthcare come together in the idea of Health Agents. This Web3 genAI tool for automated health management, specifically via digital-biological twins and pathway2vec approaches, demonstrates human-AI intelligence amplification and works towards healthy longevity for global well-being.","PeriodicalId":516827,"journal":{"name":"Proceedings of the AAAI Symposium Series","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141120716","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Framework for Enhancing Behavioral Science Research with Human-Guided Language Models","authors":"J. Scheuerman, Dina M. Acklin","doi":"10.1609/aaaiss.v3i1.31206","DOIUrl":"https://doi.org/10.1609/aaaiss.v3i1.31206","url":null,"abstract":"Many behavioral science studies result in large amounts of unstructured data sets that are costly to code and analyze, requiring multiple reviewers to agree on systematically chosen concepts and themes to categorize responses. Large language models (LLMs) have potential to support this work, demonstrating capabilities for categorizing, summarizing, and otherwise organizing unstructured data. In this paper, we consider that although LLMs have the potential to save time and resources performing coding on qualitative data, the implications for behavioral science research are not yet well understood. Model bias and inaccuracies, reliability, and lack of domain knowledge all necessitate continued human guidance. New methods and interfaces must be developed to enable behavioral science researchers to efficiently and systematically categorize unstructured data together with LLMs. We propose a framework for incorporating human feedback into an annotation workflow, leveraging interactive machine learning to provide oversight while improving a language model's predictions over time.","PeriodicalId":516827,"journal":{"name":"Proceedings of the AAAI Symposium Series","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141122765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GenAI and Socially Responsible AI in Natural Language Processing Applications: A Linguistic Perspective","authors":"Christina Alexandris","doi":"10.1609/aaaiss.v3i1.31230","DOIUrl":"https://doi.org/10.1609/aaaiss.v3i1.31230","url":null,"abstract":"It is a widely-accepted fact that the processing of very large amounts of data with state-of-the-art Natural Language Processing (NLP) practices (i.e. Machine Learning –ML, language agnostic approaches) has resulted to a dramatic improvement in the speed and efficiency of systems and applications. However, these developments are accompanied with several challenges and difficulties that have been voiced within the last years. Specifically, in regard to NLP, evident improvement in the speed and efficiency of systems and applications with GenAI also entails some aspects that may be problematic, especially when particular text types, languages and/or user groups are concerned.\u0000State-of-the-art NLP approaches with automated processing of vast amounts of data in GenAI are related to observed problematic Aspects 1-7, namely: (1) Underrepresentation, (2) Standardization. These result to (3) Barriers in Text Understanding, (4) Discouragement of HCI Usage for Special Text Types and/or User Groups, (5) Barriers in Accessing Information, (6) Likelihood of Errors and False Assumptions and (7) Difficulties in Error Detection and Recovery. An additional problem are typical cases, such as less-resourced languages (A), less experienced users (B) and less agile users (C). \u0000A hybrid approach involving the re-introduction and integration of traditional concepts in state-of-the-art processing approaches, whether they are automatic or interactive, concerns the following targets:\u0000i), (ii) and (iii): Making more types of information accessible to more types of recipients and user groups (i), Making more types of services accessible and user-friendly to more types of user groups (ii), Making more types of feelings, opinions, voices and reactions visible from more types of user groups (iii)\u0000Specifically, in the above-presented cases traditional and classical theories, principles and models are re-introduced and can be integrated into state-of-the art data-driven approaches involving Machine Learning and neural networks, functioning as training data and seed data in Natural Language Processing applications where user requirements and customization are of particular interest and importance. A hybrid approach may be considered a compromise between speed and correctness / userfriendliness in (types of) NLP applications where the achievement of this balance plays a crucial role. In other words, a hybrid approach and the examples presented here target to prevent mechanisms from adopting human biases, ensuring fairness and socially responsible outcome and responsible Social Media. A hybrid approach and the examples presented here also target to customizing content to different linguistic and cultural groups, ensuring equitable information distribution. \u0000Here, we present characteristic examples with cases employing the re-introduction of four typical types of traditional concepts concerning classical theories, principles and models. These four typical classical theories, principl","PeriodicalId":516827,"journal":{"name":"Proceedings of the AAAI Symposium Series","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141123250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Exploring Study on Building Affective Artificial Intelligence by Neural-Symbolic Computing (Extended Abstract)","authors":"Jonathan C.H. Tong, Yung-Fong Hsu, C. Liau","doi":"10.1609/aaaiss.v3i1.31288","DOIUrl":"https://doi.org/10.1609/aaaiss.v3i1.31288","url":null,"abstract":"This short paper is the status report of a project in progress. We aim to model human-like agents' decision-making behaviors under risks with neural-symbolic approach. Our model integrates the learning, reasoning, and emotional aspects of an agent and takes the dual process thinking into consideration when the agent is making a decision. The model construction is based on real behavioral and brain imaging data collected in a lottery gambling experiment. We present the model architecture including its main modules and the interactions between them.","PeriodicalId":516827,"journal":{"name":"Proceedings of the AAAI Symposium Series","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141121734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reconciling Privacy and Byzantine-robustness in Federated Learning","authors":"Lun Wang","doi":"10.1609/aaaiss.v3i1.31229","DOIUrl":"https://doi.org/10.1609/aaaiss.v3i1.31229","url":null,"abstract":"In this talk, we will discuss how to make federated learning\u0000secure for the server and private for the clients simultaneously.\u0000Most prior efforts fall into either of the two categories.\u0000At one end of the spectrum, some work uses techniques\u0000like secure aggregation to hide the individual client’s\u0000updates and only reveal the aggregated global update to a\u0000malicious server that strives to infer the clients’ privacy from\u0000their updates. At the other end of the spectrum, some work\u0000uses Byzantine-robust FL protocols to suppress the influence\u0000of malicious clients’ updates. We present a protocol that offers\u0000bidirectional defense to simultaneously combat against\u0000the malicious centralized server and Byzantine malicious\u0000clients. Our protocol also improves the dimension dependence\u0000and achieve a near-optimal statistical rate for strongly\u0000convex cases.","PeriodicalId":516827,"journal":{"name":"Proceedings of the AAAI Symposium Series","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141123417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TinyML4D: Scaling Embedded Machine Learning Education in the Developing World","authors":"Brian Plancher, Sebastian Buttrich, Jeremy Ellis, Neena Goveas, Laila Kazimierski, Jesus Lopez Sotelo, Milan Lukic, Diego Mendez, Rosdiadee Nordin, Andres Oliva Trevisan, Massimo Pavan, Manuel Roveri, Marcus Rüb, Jackline Tum, Marian Verhelst, Salah Abdeljabar, Segun Adebayo, Thomas Amberg, H. Aworinde, José Bagur, Gregg Barrett, Nabil Benamar, Bharat Chaudhari, Ronald Criollo, David Cuartielles, J. A. Ferreira Filho, Solomon Gizaw, Evgeni Gousev, Alessandro Grande, Shawn Hymel, Peter Ing, Prashant Manandhar, Pietro Manzoni, Boris Murmann, Eric Pan, R. Paskauskas, Ermanno Pietrosemoli, Tales Pimenta, Marcelo Rovai, Marco Zennaro, Vijay Janapa Reddi","doi":"10.1609/aaaiss.v3i1.31265","DOIUrl":"https://doi.org/10.1609/aaaiss.v3i1.31265","url":null,"abstract":"Embedded machine learning (ML) on low-power devices, also known as \"TinyML,\" enables intelligent applications on accessible hardware and fosters collaboration across disciplines to solve real-world problems. Its interdisciplinary and practical nature makes embedded ML education appealing, but barriers remain that limit its accessibility, especially in developing countries. Challenges include limited open-source software, courseware, models, and datasets that can be used with globally accessible heterogeneous hardware. Our vision is that with concerted effort and partnerships between industry and academia, we can overcome such challenges and enable embedded ML education to empower developers and researchers worldwide to build locally relevant AI solutions on low-cost hardware, increasing diversity and sustainability in the field. Towards this aim, we document efforts made by the TinyML4D community to scale embedded ML education globally through open-source curricula and introductory workshops co-created by international educators. We conclude with calls to action to further develop modular and inclusive resources and transform embedded ML into a truly global gateway to embedded AI skills development.","PeriodicalId":516827,"journal":{"name":"Proceedings of the AAAI Symposium Series","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141122099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Decomposed Inductive Procedure Learning: Learning Academic Tasks with Human-Like Data Efficiency","authors":"Daniel Weitekamp","doi":"10.1609/aaaiss.v3i1.31289","DOIUrl":"https://doi.org/10.1609/aaaiss.v3i1.31289","url":null,"abstract":"Human brains have many differently functioning regions which play specialized roles in learning. By contrast, methods for training artificial neural networks, such as reinforcement-learning, typically learn exclusively via a single mechanism: gradient descent. This raises the question: might human learners’ advantage in learning efficiency over deep-learning be attributed to the interplay between multiple specialized mechanisms of learning? In this work we review a series of simulated learner systems which have been built with the aim of modeling human student’s inductive learning as they practice STEM procedural tasks. By comparison to modern deep-learning based methods which train on thousands to millions of examples to acquire passing performance capabilities, these simulated learners match human performance curves---achieving passing levels of performance within about a dozen practice opportunities. We investigate this impressive learning efficiency via an ablation analysis. Beginning with end-to-end reinforcement learning (1-mechanism), we decompose learning systems incrementally to construct the 3-mechanism inductive learning characteristic of prior simulated learners such as Sierra, SimStudent and the Apprentice Learner Architecture. Our analysis shows that learning decomposition plays a significant role in achieving data-efficient learning on par with human learners---a greater role even than simple distinctions between symbolic/subsymbolic learning. Finally we highlight how this breakdown in learning mechanisms can flexibly incorporate diverse forms of natural language and interface grounded instruction, and discuss opportunities for using these flexible learning capabilities in interactive task learning systems that learn directly from a user’s natural instruction.","PeriodicalId":516827,"journal":{"name":"Proceedings of the AAAI Symposium Series","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141121775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Analysis Method for the Impact of GenAI Code Suggestions on Software Engineers’ Thought Processes","authors":"Takahiro Yonekawa, Hiroko Yamano, Ichiro Sakata","doi":"10.1609/aaaiss.v3i1.31257","DOIUrl":"https://doi.org/10.1609/aaaiss.v3i1.31257","url":null,"abstract":"Interactive generative AI can be used in software programming to generate sufficient quality of code. Software developers can utilize the output code of generative AI as well as website resources from search engine results. In this research, we present a framework for defining states of programming activity and for capturing the actions of developers in a time series.\u0000We also describe a scheme for analyzing the thought process of software developers by using a graph structure to describe state transitions. By applying these means, we showed that it is feasible to analyze the effects of changes in the development environment on programming activities.","PeriodicalId":516827,"journal":{"name":"Proceedings of the AAAI Symposium Series","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141121065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Engineering Approach to Explore Language Reflecting Well-Being","authors":"Kazuhiro Ito, Junko Hayashi, Shoko Wakamiya, Masae Manabe, Yasushi Watanabe, Masataka Nakayama, Yukiko Uchida, E. Aramaki","doi":"10.1609/aaaiss.v3i1.31235","DOIUrl":"https://doi.org/10.1609/aaaiss.v3i1.31235","url":null,"abstract":"Although well-being is helpful in measuring the state of society from various perspectives, past research has been limited to (1) questionnaire surveys, which make it difficult to target a large number of people, and (2) the major indices focus on individual factors and do not incorporate group factors. To tackle these issues, we collected daily reports from the company employees that included text, their individual subjective well-being, and team subjective well-being. By using the collected data, we constructed a well-being estimation model based on the Large Language Model and examined an indicator called ``sharedness index'', as a state of the team that influences an individual well-being, measured using both score- and text-based methods.","PeriodicalId":516827,"journal":{"name":"Proceedings of the AAAI Symposium Series","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141121504","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cultural Algorithm Guided Policy Gradient with Parameter Exploration","authors":"Mark Nuppnau, Khalid Kattan, R. G. Reynolds","doi":"10.1609/aaaiss.v3i1.31240","DOIUrl":"https://doi.org/10.1609/aaaiss.v3i1.31240","url":null,"abstract":"This study explores the integration of cultural algorithms (CA) with the Policy Gradients with Parameter-Based Exploration (PGPE) algorithm for the task of MNIST hand-written digit classification within the EvoJAX framework. The PGPE algorithm is enhanced by incorporating a belief space, consisting on Domain, Situational, and History knowledge sources (KS), to guide the search process and improve convergence speed. The PGPE algorithm, implemented within the EvoJAX framework, can efficiently find an optimal parameter-space policy for the MNIST task. However, increasing the complexity of the task and policy space, such as the CheXpert dataset and DenseNet, requires a more sophisticated approach to efficiently navigate the search space. We introduce CA-PGPE, a novel approach that integrates CA with PGPE to guide the search process and improve convergence speed. Future work will focus on incorporating exploratory knowledge sources and evaluate the enhanced CA-PGPE algorithm on more complex datasets and model architectures, such as CIFAR-10 and CheXpert with DenseNet.","PeriodicalId":516827,"journal":{"name":"Proceedings of the AAAI Symposium Series","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141122359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}