Deutsche Jahrestagung für Künstliche Intelligenz最新文献

PapagAI: Automated Feedback for Reflective Essays PapagAI:反思性论文的自动反馈

Deutsche Jahrestagung für Künstliche Intelligenz Pub Date : 2023-07-10 DOI: 10.48550/arXiv.2307.07523

Veronika Solopova, Adrian Gruszczynski, Eiad Rostom, Fritz Cremer, Sascha Witte, Chengming Zhang, Fernando Ramos L'opez Lea Plossl, Florian Hofmann, R. Romeike, Michaela Glaser-Zikuda, C. Benzmuller, Tim Landgraf

引用次数: 0

Ontology Pre-training for Poison Prediction 毒物预测的本体预训练

Deutsche Jahrestagung für Künstliche Intelligenz Pub Date : 2023-01-20 DOI: 10.48550/arXiv.2301.08577

Martin Glauer, F. Neuhaus, T. Mossakowski, J. Hastings

{"title":"Ontology Pre-training for Poison Prediction","authors":"Martin Glauer, F. Neuhaus, T. Mossakowski, J. Hastings","doi":"10.48550/arXiv.2301.08577","DOIUrl":"https://doi.org/10.48550/arXiv.2301.08577","url":null,"abstract":"Integrating human knowledge into neural networks has the potential to improve their robustness and interpretability. We have developed a novel approach to integrate knowledge from ontologies into the structure of a Transformer network which we call ontology pre-training: we train the network to predict membership in ontology classes as a way to embed the structure of the ontology into the network, and subsequently fine-tune the network for the particular prediction task. We apply this approach to a case study in predicting the potential toxicity of a small molecule based on its molecular structure, a challenging task for machine learning in life sciences chemistry. Our approach improves on the state of the art, and moreover has several additional benefits. First, we are able to show that the model learns to focus attention on more meaningful chemical groups when making predictions with ontology pre-training than without, paving a path towards greater robustness and interpretability. Second, the training time is reduced after ontology pre-training, indicating that the model is better placed to learn what matters for toxicity prediction with the ontology pre-training than without. This strategy has general applicability as a neuro-symbolic approach to embed meaningful semantics into neural networks.","PeriodicalId":303369,"journal":{"name":"Deutsche Jahrestagung für Künstliche Intelligenz","volume":"120 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114087293","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}

引用次数: 0

Automated Kantian Ethics: A Faithful Implementation 自动化康德伦理学:忠实的实现

Deutsche Jahrestagung für Künstliche Intelligenz Pub Date : 2022-07-20 DOI: 10.48550/arXiv.2207.10152

Lavanya Singh

{"title":"Automated Kantian Ethics: A Faithful Implementation","authors":"Lavanya Singh","doi":"10.48550/arXiv.2207.10152","DOIUrl":"https://doi.org/10.48550/arXiv.2207.10152","url":null,"abstract":"As we grant artificial intelligence increasing power and independence in contexts like healthcare, policing, and driving, AI faces moral dilemmas but lacks the tools to solve them. Warnings from regulators, philosophers, and computer scientists about the dangers of unethical artificial intelligence have spurred interest in automated ethics-i.e., the development of machines that can perform ethical reasoning. However, prior work in automated ethics rarely engages with philosophical literature. Philosophers have spent centuries debating moral dilemmas so automated ethics will be most nuanced, consistent, and reliable when it draws on philosophical literature. In this paper, I present an implementation of automated Kantian ethics that is faithful to the Kantian philosophical tradition. I formalize Kant's categorical imperative in Dyadic Deontic Logic, implement this formalization in the Isabelle theorem prover, and develop a testing framework to evaluate how well my implementation coheres with expected properties of Kantian ethic. My system is an early step towards philosophically mature ethical AI agents and it can make nuanced judgements in complex ethical dilemmas because it is grounded in philosophical literature. Because I use an interactive theorem prover, my system's judgements are explainable.","PeriodicalId":303369,"journal":{"name":"Deutsche Jahrestagung für Künstliche Intelligenz","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117306592","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}

引用次数: 0

Solving the Traveling Salesperson Problem with Precedence Constraints by Deep Reinforcement Learning 基于深度强化学习的优先约束旅行销售员问题求解

Deutsche Jahrestagung für Künstliche Intelligenz Pub Date : 2022-07-04 DOI: 10.1007/978-3-031-15791-2_14

Christian Löwens, Inaam Ashraf, Alexander Gembus, Genesis Cuizon, Jonas K. Falkner, L. Schmidt-Thieme

引用次数: 2

Unsupervised Alignment of Distributional Word Embeddings 分布词嵌入的无监督对齐

Deutsche Jahrestagung für Künstliche Intelligenz Pub Date : 2022-03-09 DOI: 10.48550/arXiv.2203.04863

Aïssatou Diallo

引用次数: 0

Enabling Supervised Machine Learning Through Data Pooling: A Case Study with Small and Medium-Sized Enterprises in the Service Industry 通过数据池实现监督机器学习:以服务业中小企业为例研究

Deutsche Jahrestagung für Künstliche Intelligenz Pub Date : 2022-01-01 DOI: 10.1007/978-3-031-15791-2_6

Leonhard Czarnetzki, Fabian Kainz, Fabian Lächler, Catherine Laflamme, Daniel Bachlechner

引用次数: 0

Explanation as a Process: User-Centric Construction of Multi-level and Multi-modal Explanations 作为过程的解释:以用户为中心的多层次多模态解释构建

Deutsche Jahrestagung für Künstliche Intelligenz Pub Date : 2021-10-07 DOI: 10.1007/978-3-030-87626-5_7

Bettina Finzel, David E. Tafler, Stephan Scheele, Ute Schmid

引用次数: 9

Self-Supervised Domain Adaptation for Diabetic Retinopathy Grading using Vessel Image Reconstruction 基于血管图像重建的自监督域自适应糖尿病视网膜病变分级

Deutsche Jahrestagung für Künstliche Intelligenz Pub Date : 2021-07-20 DOI: 10.1007/978-3-030-87626-5_26

D. M. Nguyen, T. Mai, Ngoc T. T. Than, Alexander Prange, Daniel Sonntag

引用次数: 3

The Randomness of Input Data Spaces is an A Priori Predictor for Generalization 输入数据空间的随机性是泛化的先验预测因子

Deutsche Jahrestagung für Künstliche Intelligenz Pub Date : 2021-06-08 DOI: 10.1007/978-3-031-15791-2_3

Martin Briesch, Dominik Sobania, Franz Rothlauf

引用次数: 1

Combining Transformer Generators with Convolutional Discriminators 变压器发生器与卷积鉴别器的结合

Deutsche Jahrestagung für Künstliche Intelligenz Pub Date : 2021-05-21 DOI: 10.1007/978-3-030-87626-5_6

R. Durall, Stanislav Frolov, A. Dengel, J. Keuper

引用次数: 14