Obserwuj
Louis Kirsch
Louis Kirsch
The Swiss AI Lab IDSIA
Zweryfikowany adres z idsia.ch - Strona główna
Tytuł
Cytowane przez
Cytowane przez
Rok
Transfer Learning for Speech Recognition on a Budget
J Kunze, L Kirsch, I Kurenkov, A Krug, J Johannsmeier, S Stober
ACL 2017, 168, 2017
1702017
Improving Generalization in Meta Reinforcement Learning using Learned Objectives
L Kirsch, S van Steenkiste, J Schmidhuber
arXiv preprint arXiv:1910.04098, 2019
1352019
Modular Networks: Learning to Decompose Neural Computation
L Kirsch, J Kunze, D Barber
Advances in Neural Information Processing Systems, 2408-2418, 2018
1232018
Meta Learning Backpropagation And Improving It
L Kirsch, J Schmidhuber
4th Workshop on Meta-Learning at NeurIPS 2020, 2020
682020
General-Purpose In-Context Learning by Meta-Learning Transformers
L Kirsch, J Harrison, J Sohl-Dickstein, L Metz
arXiv preprint arXiv:2212.04458, 2022
472022
Introducing symmetries to black box meta reinforcement learning
L Kirsch, S Flennerhag, H van Hasselt, A Friesen, J Oh, Y Chen
Proceedings of the AAAI Conference on Artificial Intelligence 36 (7), 7202-7210, 2022
312022
Mindstorms in Natural Language-Based Societies of Mind
M Zhuge, H Liu, F Faccio, DR Ashley, R Csordás, A Gopalakrishnan, ...
arXiv preprint arXiv:2305.17066, 2023
282023
Parameter-based value functions
F Faccio, L Kirsch, J Schmidhuber
arXiv preprint arXiv:2006.09226, 2020
242020
Brain-inspired learning in artificial neural networks: a review
S Schmidgall, J Achterberg, T Miconi, L Kirsch, R Ziaei, S Hajiseyedrazi, ...
arXiv preprint arXiv:2305.11252, 2023
132023
The Benefits of Model-Based Generalization in Reinforcement Learning
K Young, A Ramesh, L Kirsch, J Schmidhuber
arXiv preprint arXiv:2211.02222, 2022
122022
Goal-conditioned generators of deep policies
F Faccio, V Herrmann, A Ramesh, L Kirsch, J Schmidhuber
Proceedings of the AAAI Conference on Artificial Intelligence 37 (6), 7503-7511, 2023
102023
Self-Referential Meta Learning
L Kirsch, J Schmidhuber
First Conference on Automated Machine Learning (Late-Breaking Workshop), 2022
92022
Eliminating Meta Optimization Through Self-Referential Meta Learning
L Kirsch, J Schmidhuber
arXiv preprint arXiv:2212.14392, 2022
82022
Exploring through random curiosity with general value functions
A Ramesh, L Kirsch, S van Steenkiste, J Schmidhuber
Advances in Neural Information Processing Systems 35, 18733-18748, 2022
72022
Learning One Abstract Bit at a Time Through Self-Invented Experiments Encoded as Neural Networks
V Herrmann, L Kirsch, J Schmidhuber
arXiv preprint arXiv:2212.14374, 2022
32022
Gaussian mean field regularizes by limiting learned information
J Kunze, L Kirsch, H Ritter, D Barber
Entropy 21 (8), 758, 2019
32019
Towards General-Purpose In-Context Learning Agents
L Kirsch, J Harrison, C Freeman, J Sohl-Dickstein, J Schmidhuber
NeurIPS 2023 Foundation Models for Decision Making Workshop, 2023
22023
Discovering Temporally-Aware Reinforcement Learning Algorithms
MT Jackson, C Lu, L Kirsch, RT Lange, S Whiteson, JN Foerster
Second Agent Learning in Open-Endedness Workshop, 2023
12023
The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute
A Stanić, D Ashley, O Serikov, L Kirsch, F Faccio, J Schmidhuber, ...
arXiv preprint arXiv:2309.11197, 2023
12023
Scaling Neural Networks Through Sparsity
L Kirsch
Tech. rep, 2018
12018
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–20