Keller, T. A., & Welling, M. (2022). Topographic VAEs learn Equivariant Capsules. In M. Ranzato, A. Beygelzimer, Y. Dauphin, P. S. Liang, & J. Wortman Vaughan (Eds.), 35th Conference on Neural Information Processing Systems (NeurIPS 2021) : online, 6-14 December 2021 (Vol. 34, pp. 28585-28597). (Advances in Neural Information Processing Systems; Vol. 34). Neural Information Processing Systems Foundation. https://doi.org/10.48550/arXiv.2109.01394[details]
Keller, T. A., & Welling, M. (2021). Predictive Coding with Topographic Variational Autoencoders. In 2021 IEEE/CVF International Conference on Computer Vision Workshops: proceedings : ICCVW 2021 : 11-17 October 2021, virtual event (pp. 1086-1091). IEEE Computer Society. https://doi.org/10.1109/ICCVW54120.2021.00127[details]
Keller, T. A., Peters, J. W. T., Jaini, P., Hoogeboom, E., Forré, P., & Welling, M. (2021). Self Normalizing Flows. Proceedings of Machine Learning Research, 139, 5378-5387. https://arxiv.org/abs/2011.07248[details]
Keller, T. A., Gao, Q., & Welling, M. (2021). Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders. Paper presented at 3rd Workshop on Shared Visual Representations in Human and Machine Intelligence of the Neural Information Processing Systems conference. https://arxiv.org/abs/2110.13911
Wever, F., Keller, T. A., García Satorras, V., & Symul, L. (2021). As easy as APC: Leveraging self-supervised learning in the context of time series classification with varying levels of sparsity and severe class imbalance.. Paper presented at 2nd Workshop on Self-Supervised Learning: Theory and Practice of the 35th Conference on Neural Information Processing Systems. https://arxiv.org/abs/2106.15577
2023
Keller, T. A. (2023). Natural inductive biases for artificial intelligence. [Thesis, fully internal, Universiteit van Amsterdam]. [details]
Liboni, L., Budzinski, R., Busch, A., Löwe, S., Keller, T. A., Welling, M., & Muller, L. (2023). Image segmentation with traveling waves in an exactly solvable recurrent neural network.
De UvA gebruikt cookies voor het meten, optimaliseren en goed laten functioneren van de website. Ook worden er cookies geplaatst om inhoud van derden te kunnen tonen en voor marketingdoeleinden. Klik op ‘Accepteer alle cookies’ om akkoord te gaan met het plaatsen van alle cookies. Of kies voor ‘Weigeren’ om alleen functionele en analytische cookies te accepteren. Lees ook het UvA Privacy statement.