Следене
Xu Ji
Xu Ji
Mila
Потвърден имейл адрес: mila.quebec
Заглавие
Позовавания
Позовавания
Година
Invariant Information Clustering for Unsupervised Image Classification and Segmentation
X Ji, JF Henriques, A Vedaldi
arXiv preprint arXiv:1807.06653, 2019
9452019
There and back again: Revisiting backpropagation saliency methods
SA Rebuffi, R Fong, X Ji, A Vedaldi
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020
1252020
Consciousness in artificial intelligence: insights from the science of consciousness
P Butlin, R Long, E Elmoznino, Y Bengio, J Birch, A Constant, G Deane, ...
arXiv preprint arXiv:2308.08708, 2023
422023
GFlowNets and variational inference
N Malkin, S Lahlou, T Deleu, X Ji, E Hu, K Everett, D Zhang, Y Bengio
arXiv preprint arXiv:2210.00580, 2022
372022
How does information bottleneck help deep learning?
K Kawaguchi, Z Deng, X Ji, J Huang
International Conference on Machine Learning, 16049-16096, 2023
162023
On the role of neurogenesis in overcoming catastrophic forgetting
GI Parisi, X Ji, S Wermter
arXiv preprint arXiv:1811.02113, 2018
162018
Automatic recall machines: Internal replay, continual learning and the brain
X Ji, J Henriques, T Tuytelaars, A Vedaldi
arXiv preprint arXiv:2006.12323, 2020
112020
Gflowout: Dropout with generative flow networks
D Liu, M Jain, BFP Dossou, Q Shen, S Lahlou, A Goyal, N Malkin, ...
International Conference on Machine Learning, 21715-21729, 2023
102023
Adaptive discrete communication bottlenecks with dynamic vector quantization
D Liu, A Lamb, X Ji, P Notsawo, M Mozer, Y Bengio, K Kawaguchi
arXiv preprint arXiv:2202.01334, 2022
92022
Test Sample Accuracy Scales with Training Sample Density in Neural Networks
X Ji, R Pascanu, D Hjelm, B Lakshminarayanan, A Vedaldi
arXiv preprint arXiv:2106.08365, 2021
9*2021
Sources of richness and ineffability for phenomenally conscious states
X Ji, E Elmoznino, G Deane, A Constant, G Dumas, G Lajoie, J Simon, ...
Neuroscience of Consciousness 2024 (1), niae001, 2024
72024
Graph-Based Active Machine Learning Method for Diverse and Novel Antimicrobial Peptides Generation and Selection
BFP Dossou, D Liu, X Ji, M Jain, AM van der Sloot, R Palou, M Tyers, ...
12022
Unsupervised learning and continual learning in neural networks
X Ji
University of Oxford, 2021
12021
Adaptive discrete communication bottlenecks with dynamic vector quantization for heterogeneous representational coarseness
D Liu, A Lamb, X Ji, PJT Notsawo, M Mozer, Y Bengio, K Kawaguchi
Proceedings of the AAAI Conference on Artificial Intelligence 37 (7), 8825-8833, 2023
2023
An Analysis of Information Bottlenecks
K Kawaguchi, X Ji, J Huang, Y Bengio
2022
Properties of Minimizing Entropy
X Ji, L Nehale-Ezzine, M Korablyov
arXiv preprint arXiv:2112.03143, 2021
2021
La Conciencia en la Inteligencia Artificial: Reflexiones desde la Ciencia de la Conciencia
P Butlin, R Long, E Elmoznino, Y Bengio, J Birch, A Constant, G Deane, ...
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–17