Alexander Lerchner
Alexander Lerchner
Senior Staff Scientist, Google DeepMind
Verified email at
Cited by
Cited by
beta-vae: Learning basic visual concepts with a constrained variational framework.
I Higgins, L Matthey, A Pal, CP Burgess, X Glorot, MM Botvinick, ...
ICLR (Poster) 3, 2017
Understanding disentangling in -VAE
CP Burgess, I Higgins, A Pal, L Matthey, N Watters, G Desjardins, ...
arXiv preprint arXiv:1804.03599, 2018
Towards a definition of disentangled representations
I Higgins, D Amos, D Pfau, S Racaniere, L Matthey, D Rezende, ...
arXiv preprint arXiv:1812.02230, 2018
Monet: Unsupervised scene decomposition and representation
CP Burgess, L Matthey, N Watters, R Kabra, I Higgins, M Botvinick, ...
arXiv preprint arXiv:1901.11390, 2019
Darla: Improving zero-shot transfer in reinforcement learning
I Higgins, A Pal, A Rusu, L Matthey, C Burgess, A Pritzel, M Botvinick, ...
International Conference on Machine Learning, 1480-1490, 2017
Multi-object representation learning with iterative variational inference
K Greff, RL Kaufman, R Kabra, N Watters, C Burgess, D Zoran, L Matthey, ...
International conference on machine learning, 2424-2433, 2019
dsprites: Disentanglement testing sprites dataset
L Matthey, I Higgins, D Hassabis, A Lerchner
Unsupervised Model Selection for Variational Disentangled Representation Learning
S Duan, L Matthey, A Saraiva, N Watters, CP Burgess, A Lerchner, ...
arXiv preprint arXiv:1905.12614, 2019
Early visual concept learning with unsupervised deep learning
I Higgins, L Matthey, X Glorot, A Pal, B Uria, C Blundell, S Mohamed, ...
arXiv preprint arXiv:1606.05579, 2016
International Conference on Learning Representations
I Higgins, L Matthey, A Pal, C Burgess, X Glorot, M Botvinick, S Mohamed, ...
ICLR 2017, Toulon, France, 2017
Spatial broadcast decoder: A simple architecture for learning disentangled representations in vaes
N Watters, L Matthey, CP Burgess, A Lerchner
arXiv preprint arXiv:1901.07017, 2019
Scan: Learning hierarchical compositional visual concepts
I Higgins, N Sonnerat, L Matthey, A Pal, CP Burgess, M Bosnjak, ...
arXiv preprint arXiv:1707.03389, 2017
Life-long disentangled representation learning with cross-domain latent homologies
A Achille, T Eccles, L Matthey, C Burgess, N Watters, A Lerchner, ...
Advances in Neural Information Processing Systems 31, 2018
Cobra: Data-efficient model-based rl through unsupervised object discovery and curiosity-driven exploration
N Watters, L Matthey, M Bosnjak, CP Burgess, A Lerchner
arXiv preprint arXiv:1905.09275, 2019
Multi-object datasets
R Kabra, C Burgess, L Matthey, RL Kaufman, K Greff, M Reynolds, ...
DeepMind 5 (6), 7, 2019
Simone: View-invariant, temporally-abstracted object representations via unsupervised video decomposition
R Kabra, D Zoran, G Erdogan, L Matthey, A Creswell, M Botvinick, ...
Advances in Neural Information Processing Systems 34, 20146-20159, 2021
Response variability in balanced cortical networks
A Lerchner, C Ursta, J Hertz, M Ahmadi, P Ruffiot, S Enemark
Neural computation 18 (3), 634-659, 2006
Understanding disentangling in β
CP Burgess, I Higgins, A Pal, L Matthey, N Watters, G Desjardins, ...
arXiv preprint arXiv:1804.03599, 2018
Parts: Unsupervised segmentation with slots, attention and independence maximization
D Zoran, R Kabra, A Lerchner, DJ Rezende
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
Mean field theory for a balanced hypercolumn model of orientation selectivity in primary visual cortex
A Lerchner, G Sterner, J Hertz, M Ahmadi
Network: Computation in Neural Systems 17 (2), 131-150, 2006
The system can't perform the operation now. Try again later.
Articles 1–20