Filtrer vos résultats
- 6
- 4
- 2
- 6
- 1
- 4
- 1
- 1
- 6
- 5
- 4
- 1
- 1
- 1
- 5
- 4
- 3
- 2
- 1
- 1
- 1
6 résultats
|
|
triés par
|
|
Block-wise Training of Residual Networks via the Minimizing Movement Scheme1st International Workshop on Practical Deep Learning in the Wild at 26th AAAI Conference on Artificial Intelligence 2022, AAAI, Feb 2022, Vancouver, Canada
Communication dans un congrès
hal-04108676v1
|
||
|
Unveiling the Transport Dynamics of Neural Networks : a Least Action Principle for Deep LearningNeural and Evolutionary Computing [cs.NE]. Sorbonne Université, 2023. English. ⟨NNT : 2023SORUS306⟩
Thèse
tel-04296347v1
|
||
|
Unveiling the Transport Dynamics of Neural Networks: A Least Action Principle for Deep LearningArtificial Intelligence [cs.AI]. Sorbonne Université, 2023. English. ⟨NNT : 2023SORUS306⟩
Thèse
tel-04294849v1
|
||
|
A Principle of Least Action for the Training of Neural NetworksECML PKDD, Sep 2020, Ghent, Belgium
Communication dans un congrès
hal-03038615v1
|
||
|
Module-wise Training of Neural Networks via the Minimizing Movement SchemeThirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), Dec 2023, New Orleans (Louisiana), United States
Communication dans un congrès
hal-04223364v1
|
||
|
Adversarial Sample Detection Through Neural Network Transport DynamicsEuropean Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2023), Sep 2023, Torino, Italy
Communication dans un congrès
hal-04120861v1
|