A growing number of embedded applications, confronted with diversified, shifting, and uncontrolled environments, require an increased degree of adaptability and analysis capabilities to fulfill their task. Pre-programmed actions are no longer able to deal with these new sets of tasks and are therefore being replaced by a promising paradigm: deep learning. However, deep neural networks are susceptible to data distribution shifts occurring between training and use. This apparent flaw prevents the widespread deployment of deep networks in embedded products. Furthermore, it is impossible to gather and add enough data to the training set to cover all possible shifts due to their tremendous diversity. The origin of this vulnerability lies partl...
Domain adaptation allows machine learning models to perform well in a domain that is different from ...
Machine learning consists in the study and design of algorithms that build models able to handle non...
Large-scale deep learning models have reached previously unattainable performance for various tasks....
Recent studies reveal that a deep neural network can learn transferable features which generalize we...
National audienceDomain Adaptation methods seek to generalize the knowledge learned on a labeled sou...
In the field of machine learning, deep neural networks have become the inescapablereference for a ve...
This thesis tackles some of the scientific locks of perception systems based on neural networks for ...
In the context of supervised statistical learning, it is typically assumed that the training set com...
Recent approaches based on end-to-end deep neural networks have revolutionised Natural Language Proc...
Domain adaptation aims to alleviate the gap between different data distributions, commonly referred ...
Neural network models and deep models are one of the leading and state of the art models in machine ...
Deep neural networks suffer from significant performance deterioration when there exists distributio...
This thesis will present a number of investigations into how machine learning systems, in particula...
International audienceDeep neural networks often fail to generalize outside of their training distri...
Deep learning has emerged as a powerful approach for modelling static data like images and more rece...
Domain adaptation allows machine learning models to perform well in a domain that is different from ...
Machine learning consists in the study and design of algorithms that build models able to handle non...
Large-scale deep learning models have reached previously unattainable performance for various tasks....
Recent studies reveal that a deep neural network can learn transferable features which generalize we...
National audienceDomain Adaptation methods seek to generalize the knowledge learned on a labeled sou...
In the field of machine learning, deep neural networks have become the inescapablereference for a ve...
This thesis tackles some of the scientific locks of perception systems based on neural networks for ...
In the context of supervised statistical learning, it is typically assumed that the training set com...
Recent approaches based on end-to-end deep neural networks have revolutionised Natural Language Proc...
Domain adaptation aims to alleviate the gap between different data distributions, commonly referred ...
Neural network models and deep models are one of the leading and state of the art models in machine ...
Deep neural networks suffer from significant performance deterioration when there exists distributio...
This thesis will present a number of investigations into how machine learning systems, in particula...
International audienceDeep neural networks often fail to generalize outside of their training distri...
Deep learning has emerged as a powerful approach for modelling static data like images and more rece...
Domain adaptation allows machine learning models to perform well in a domain that is different from ...
Machine learning consists in the study and design of algorithms that build models able to handle non...
Large-scale deep learning models have reached previously unattainable performance for various tasks....