Machine learning.

At the end phase of my Ph.D. in psychology, I trained myself in various machine learning techniques, especially artificial neural networks. To consolidate and advance these skills, I expanded my research focus and added a post-doc on computational modeling approaches to my career. During my time at the Neuro-Cognitive Modeling lab of Prof. Martin Butz, I investigated how artificial neural networks can be improved by including inductive biases that are inspired by human cognition and applied the empirical rigor that I had acquired during my Ph.D. to investigate the models’ inner working mechanisms.

I was a visiting scholar at Prof. Virginia de Sa’s lab at the Halıcıoğlu Data Science Institute at UC San Diego, where I applied a computer vision model to investigate a psychological research question, supported by a fellowship from the Science department of the University of Tübingen. Additionally, I was visiting Stanford University to investigate machine intuition in large language models with the help of psychological methods like the Cognitive Reflection Test.  

My past experience led to my current role at Mercedes-Benz AG, where I will be developing the Mercedes Virtual Assistant as an AI Architect.

Media appearances:

• Murphy, H. T. (10.12.2022) Who Painted That New Cosmic You? – Lensa’s trippy, A.I.-generated avatars are a viral hit. But their magic comes from an unsettling place. Slate.

Presentations:

• Fabi, S. (2022). Applying Cognitive Science to Machine Learning and vice versa. Research Talk, DeepMind, London.

• Fabi, S. (2022). Efficient learning in generative RNNs: Solving one-shot tasks by including compositionality as an inductive bias. Tech Talk, Amazon, Tübingen.

• 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, Tübingen.

• 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.

• 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).

• 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 Workshop Spatio-temporal Aspects of Embodied Predictive Processing.

• 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) – Workshop Learning to Learn.

Peer-reviewed papers:

• Hagendorff, T., Fabi, S., & Kosinski, M. (under review). Machine intuition: Uncovering human-like intuitive decision-making in GPT-3.5.

• Fabi, S., & Hagendorff, T. (under review). Why we need biased AI – How including ethical and cognitive machine biases can enhance AI systems.

• 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. In NeurIPS Workshop SyntheticData4ML.

• Fabi, S., Xu, X., & de Sa, V.R. (2022). Exploring the racial bias in pain detection with a computer vision model. Proceedings of the Annual Meeting of the Cognitive Science Society, 44.

• 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. Proceedings of the Annual Meeting of the Cognitive Science Society, 44.

• Fabi, S., Otte, S., Scholz, F., Wührer, J., Karlbauer, M., & Butz, M.V. (2022). Extending the Omniglot Challenge: Imitating handwriting styles on a new sequential data set. IEEE Transactions on Cognitive and Developmental Systems.

Fabi, S., Otte, S., & Butz, M.V. (2021). Compositionality as learning bias in generative RNNs solves the Omniglot challenge. In International Conference on Learning Representations (ICLR) – Workshop Learning to Learn.

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

Hobbhahn, M., Butz, M.V., Fabi, S., & Otte, S. (2020). Sequence classification using ensembles of recurrent generative expert modules. In Proceedings of the 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning – ESANN 2020, 333-338.

Fabi, S., Otte, S., Wiese, J.G., & Butz, M.V. (2020). Investigating efficient learning and compositionality in generative LSTM networks. In I. Farkas, P. Masulli, & S. Wermter (Eds.), Proceedings of Artificial Neural Networks and Machine Learning – ICANN 2020, 143-154.

You can find my Google Scholar profile here.