{"id":69,"date":"2022-02-10T09:16:47","date_gmt":"2022-02-10T09:16:47","guid":{"rendered":"https:\/\/sarah-fabi.com\/wpsarah\/?page_id=69"},"modified":"2025-12-18T12:40:00","modified_gmt":"2025-12-18T12:40:00","slug":"machine-learning","status":"publish","type":"page","link":"https:\/\/sarah-fabi.com\/wpsarah\/machine-learning\/","title":{"rendered":"Machine learning."},"content":{"rendered":"\n
\"\"<\/figure>
\n

In the concluding stages of my Ph.D. in psychology<\/a>, I self-taught a range of machine learning techniques, with a particular focus on artificial neural networks. This initiative led me to broaden my research scope by pursuing a postdoctoral position in computational modeling approaches. At the University of T\u00fcbingen, I explored enhancements to artificial neural networks through the integration of inductive biases inspired by human cognition. <\/p>\n<\/div><\/div>\n\n\n\n

My research journey included a tenure as a visiting scholar in Prof. Virginia de Sa’s lab at the Hal\u0131c\u0131o\u011flu Data Science Institute at UC San Diego. Here, I leveraged a computer vision model to address a psychological research question, an endeavor supported by a fellowship from the Science department of the University of T\u00fcbingen. Additionally, a visit to Stanford University enabled me to examine machine intuition in large language models through psychological methods, contributing to a publication in Nature Computational Science<\/a>.<\/p>\n\n\n\n

These experiences paved the way to my current position as an AI Researcher at Mercedes-Benz AG, where I am tasked with developing the Mercedes Virtual Assistant as well as making generative AI usable for the company.<\/p>\n\n\n\n

Media appearance:<\/em><\/p>\n\n\n\n

\u2022 Tal Murphy, H. (10.12.2022). Who painted that new cosmic you? Slate.<\/em><\/a><\/p>\n\n\n\n

Peer-reviewed papers:<\/em><\/p>\n\n\n\n

\u2022 Hagendorff, T. & Fabi, S. (2025): Beyond chains of thought: Benchmarking latent-space reasoning abilities in Large Language Models<\/strong>. In arXiv:2504.10615.<\/a><\/p>\n\n\n\n

\u2022 Hagendorff, T., Fabi, S., & Kosinski, M. (2023). Human-like intuitive behavior and reasoning biases emerged in large language models but disappeared in ChatGPT.<\/strong> Nature Computational Science, 3<\/a>.<\/p>\n\n\n\n

\u2022 Hagendorff, T. & Fabi, S. (2023). Why we need biased AI – How including cognitive biases can enhance AI systems.<\/strong> Journal of Experimental & Theoretical Artificial Intelligence.<\/a><\/p>\n\n\n\n

\u2022 Raina, R., Monares, M., Xu, M., Fabi, S., Xu, X., Li, L., Sumerfield, W., Gan, J., & Virginia R. de Sa. (2022). Exploring biases in facial expression analysis using synthetic faces.<\/strong> In NeurIPS Workshop SyntheticData4ML.<\/a><\/p>\n\n\n\n

\u2022 Fabi, S., Xu, X., & de Sa, V.R. (2022). Exploring the racial bias in pain detection with a computer vision model.<\/strong> Proceedings of the Annual Meeting of the Cognitive Science Society, 44.<\/a><\/p>\n\n\n\n

\u2022 Fabi, S., Holzwarth, L., & Butz, M.V. (2022). Efficient learning through compositionality in a CNN-RNN model consisting of a bottom-up and a top-down pathway.<\/strong> Proceedings of the Annual Meeting of the Cognitive Science Society, 44.<\/a><\/p>\n\n\n\n

\u2022 Fabi, S., Otte, S., Scholz, F., W\u00fchrer, J., Karlbauer, M., & Butz, M.V. (2022). Extending the Omniglot Challenge: Imitating handwriting styles on a new sequential data set.<\/strong> IEEE Transactions on Cognitive and Developmental Systems.<\/a><\/p>\n\n\n\n

\u2022 Fabi, S., Otte, S., & Butz, M.V. (2021). Compositionality as learning bias in generative RNNs solves the Omniglot challenge<\/strong>. In International Conference on Learning Representations (ICLR) – Workshop Learning to Learn.<\/a><\/p>\n\n\n\n

\u2022 Fabi, S., Otte, S., & Butz, M.V. (2021). Fostering compositionality in latent, generative encodings to solve the Omniglot challenge<\/strong>. In I. Farkas, P. Masulli, S. Otte, & S. Wermter (Eds.), Proceedings of Artificial Neural Networks and Machine Learning \u2013 ICANN 2021, Part II, 525-536.<\/a><\/p>\n\n\n\n

\u2022 Hobbhahn, M., Butz, M.V., Fabi, S., & Otte, S. (2020). Sequence classification using ensembles of recurrent generative expert modules<\/strong>. In Proceedings of the 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning \u2013 ESANN 2020, 333-338.<\/a><\/p>\n\n\n\n

\u2022 Fabi, S., Otte, S., Wiese, J.G., & Butz, M.V. (2020). Investigating efficient learning and compositionality in generative LSTM networks<\/strong>. In I. Farkas, P. Masulli, & S. Wermter (Eds.), Proceedings of Artificial Neural Networks and Machine Learning \u2013 ICANN 2020, 143-154.<\/a><\/p>\n\n\n\n

Media appearances: <\/em><\/p>\n\n\n\n

\u2022 Murphy, H. T. (10.12.2022) Who Painted That New Cosmic You? – Lensa\u2019s trippy, A.I.-generated avatars are a viral hit. But their magic comes from an unsettling place. Slate.<\/strong><\/a><\/p>\n\n\n\n

Presentations: <\/em><\/p>\n\n\n\n

\u2022 Fabi, S. (2022). Applying Cognitive Science to Machine Learning and vice versa. Research Talk, DeepMind, <\/strong>London.<\/p>\n\n\n\n

\u2022 Fabi, S. (2022). Efficient learning in generative RNNs: Solving one-shot tasks by including compositionality as an inductive bias. Tech Talk, Amazon<\/strong>, T\u00fcbingen.<\/p>\n\n\n\n

\u2022 Fabi, S. (2022). Machine learning for psychological research: Using the example of the racial bias in pain recognition. Machine Learning in Science: Postdoc Symposium of the Cluster of Excellence<\/strong>, T\u00fcbingen.<\/p>\n\n\n\n

\u2022 Fabi, S., Otte, S. & Butz, M.V. (2021). Fostering compositionality in generative RNNs to solve the Omniglot challenge. Oral presentation at the Computational Cognition Workshop<\/strong>.<\/p>\n\n\n\n

\u2022 Fabi, S., Otte, S., & Butz, M.V. (2021). Fostering compositionality in latent, generative encodings to solve the Omniglot challenge. Oral presentation at the 30th International Conference on Artificial Neural Networks (ICANN<\/strong>).<\/p>\n\n\n\n

\u2022 Fabi, S., Otte, S. & Butz, M.V. (2021). Does compositionality as a prior in Generative RNNs lead to efficient learning of temporal predictions?. Oral presentation at the ICDL <\/strong>Workshop Spatio-temporal Aspects of Embodied Predictive Processing.<\/p>\n\n\n\n

\u2022 Fabi,  S.,  Otte,  S.,  & Butz,  M.V. (2021). Compositionality as learning bias in generative RNNs solves the Omniglot challenge. Poster presented at International Conference on Learning Representations (ICLR<\/strong>) – Workshop Learning to Learn.<\/p>\n\n\n\n

You can find my Google Scholar profile here<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"

In the concluding stages of my Ph.D. in psychology, I self-taught a range of machine learning techniques, with a particular focus on […]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":{"0":"post-69","1":"page","2":"type-page","3":"status-publish","5":"col-md-12"},"_links":{"self":[{"href":"https:\/\/sarah-fabi.com\/wpsarah\/wp-json\/wp\/v2\/pages\/69","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/sarah-fabi.com\/wpsarah\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/sarah-fabi.com\/wpsarah\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/sarah-fabi.com\/wpsarah\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/sarah-fabi.com\/wpsarah\/wp-json\/wp\/v2\/comments?post=69"}],"version-history":[{"count":35,"href":"https:\/\/sarah-fabi.com\/wpsarah\/wp-json\/wp\/v2\/pages\/69\/revisions"}],"predecessor-version":[{"id":349,"href":"https:\/\/sarah-fabi.com\/wpsarah\/wp-json\/wp\/v2\/pages\/69\/revisions\/349"}],"wp:attachment":[{"href":"https:\/\/sarah-fabi.com\/wpsarah\/wp-json\/wp\/v2\/media?parent=69"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}