Folgen
Bart Bussmann
Bart Bussmann
Independent
Bestätigte E-Mail-Adresse bei student.uva.nl
Titel
Zitiert von
Zitiert von
Jahr
Neural additive vector autoregression models for causal discovery in time series data
B Bussmann, J Nys, S Latré
Discovery Science: 24th International Conference, DS 2021, Halifax, NS …, 2020
34*2020
Towards empathic deep q-learning
B Bussmann, J Heinerman, J Lehman
Proceedings of the Workshop on Artificial Intelligence Safety 2019 co …, 2019
132019
Inferring the relationship between soil temperature and the normalized difference vegetation index with machine learning
S Mortier, A Hamedpour, B Bussmann, RPT Wandji, S Latré, ...
Ecological Informatics 82, 102730, 2024
72024
BatchTopK Sparse Autoencoders
B Bussmann, P Leask, N Nanda
NeurIPS 2024 Workshop on Scientific Methods for Understanding Deep Learning, 2024
7*2024
Semantic segmentation of plant roots from RGB (mini-) rhizotron images—generalisation potential and false positives of established methods and advanced deep-learning models
P Baykalov, B Bussmann, R Nair, AG Smith, G Bodner, O Hadar, ...
Plant Methods 19 (1), 122, 2023
62023
Stitching saes of different sizes
B Bussmann, P Leask, J Bloom, C Tigges, N Nanda
AI Alignment Forum, 2024
3*2024
Benefits of social learning in physical robots
J Heinerman, B Bussmann, R Groenendijk, E Van Krieken, J Slik, A Tezza, ...
2018 IEEE Symposium Series on Computational Intelligence (SSCI), 851-858, 2018
22018
Sparse Autoencoders Do Not Find Canonical Units of Analysis
P Leask, B Bussmann, M Pearce, J Bloom, C Tigges, NA Moubayed, ...
arXiv preprint arXiv:2502.04878, 2025
2025
Showing sae latents are not atomic using meta-saes
B Bussmann, M Pearce, P Leask, J Bloom, L Sharkey, N Nanda
https://www.alignmentforum.org/posts/TMAmHh4DdMr4nCSr5/showing-sae-latents …, 2024
2024
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–9