Skip to main content

Thesis defence : Marion MAINSANT

Thesis defence

On 15 December 2023

Grenoble - Presqu'île

Continual learning across data arrival scenarios, a step towards real-life applications.

The human brain continuously receives information from external stimuli. It then has the ability to adapt to new knowledge while retaining past events. Nowadays, more and more artificial intelligence algorithms aim to learn knowledge in the same way as a human being. They therefore have to be able to adapt to a large variety of data arriving sequentially and available over a limited period of time. However, when a deep learning algorithm learns new data, the knowledge contained in the neural network overlaps old one and the majority of the past information is lost, a phenomenon referred in the literature as catastrophic forgetting. Numerous methods have been proposed to overcome this issue, but as they were focused on providing the best performance, studies have moved away from real-life applications where algorithms need to adapt to changing environments and perform, no matter the type of data arrival. In addition, most of the best state of the art methods are replay methods which retain a small memory of the past and consequently do not preserve data privacy. In this thesis, we propose to explore data arrival scenarios existing in the literature, with the aim of applying them to facial emotion recognition, which is essential for human-robot interactions. To this end, we present Dream Net - Data-Free, a privacy preserving algorithm, able to adapt to a large number of data arrival scenarios without storing any past samples. After demonstrating the robustness of this algorithm compared to existing state-of-the-art methods on standard computer vision databases (Mnist, Cifar-10, Cifar-100 and Imagenet-100), we show that it can also adapt to more complex facial emotion recognition databases. We then propose to embed the algorithm on a Nvidia Jetson nano card creating a demonstrator able to learn and predict emotions in real-time. Finally, we discuss the relevance of our approach for bias mitigation in artificial intelligence, opening up perspectives towards a more ethical AI.

Supervisor : Martial Mermillod

Keywords: Deep learning, Continual learning, Face emotion recognition, Personalization, Fairness, Bias mitigation, Ethical AI, Embedded AI



On 15 December 2023


Grenoble - Presqu'île

Complément lieu

à 13h dans l’Amphithéâtre M001 – Minatec - Phelma situé au 3 Parvis Louis Néel, 38000 GRENOBLE

Submitted on 20 November 2023

Updated on 22 November 2023