Interdisciplinary Institute in Artificial Intelligence

DESCRIPTION

Our research team, led by Martial Mermillod and Sophie Achard is developing bio-inspired algorithms to improve the performance of deep neural networks (DNN).

Deep Neural Networks (DNNs) have recently revealed significant limitations in various computational tasks. Our goal is (1) to use innovative mathematical algorithms to understand how DNNs solve these computational problems and (2) to develop new architectures that address these limitations more efficiently than current state-of-the-art methods.

ABOUT OUR RESEARCH

RESEARCHING BIO-INSPIRED METHODS TO IMPROVE THE ROBUSTNESS OF CONVOLUTIONAL NEURAL NETWORKS (CNNs) AGAINST ADVERSARIAL PERTURBATIONS

CNNs are affected by adversarial perturbations (Goodfellow et al., 2015), i.e., small shifts in input images that cause the CNN to misclassify the image. One explanation for this problem could be the excessive sensitivity of these networks to texture information (Geirhos et al., 2019), and more generally, because the features these networks use to classify an image appear to differ significantly from those used by humans.

Recent studies do indeed seem to indicate that CNNs use a wide range of different features to classify images, many of which are irrelevant to humans and may be excellent targets for creating adversarial perturbations. (Ilyas et al., 2019). For example, high spatial frequencies (which include texture information) are widely used by naturally trained CNNs, to the point where images filtered to such an extent that only the very high frequencies remain are still correctly categorized by state-of-the-art CNNs on datasets such as ImageNet. (Yin et al., 2019).

Why is CNN fooled by these perturbations, while human vision remains unaffected? Psychological and neuroscientific experiments have shown that the human visual system relies heavily on spatial frequency processing of visual information, as well as recurrent, proactive processing (Bar, 2007) of visual input, in which higher-level brain areas guide the lower-level vision processing areas toward the recognition of an object or a scene.

We are currently focusing on two main approaches based on these leads, namely (1) developing algorithms capable of mimicking the recurrent, spatial filtering processes that occur in the human brain, and (2) finding ways to identify the "non-robust" features of a CNN that are most vulnerable to adversarial perturbations.
 

SELECTED LIST OF PUBLICATIONS 

• Mainsant, M., Solinas, M., Reyboz, M., Godin, C., & Mermillod, M. "Dream Net: A Privacy-Preserving Continuous Learning Model for Face Emotion Recognition." Proceedings of the 9th International Conference on Affective Computing & Intelligent Interaction (ACII 2021).
   
• Cohendet, R., Solinas, M., Bernhard, R., Reyboz, M., Moellic, P.A., Bourrier, Y., & Mermillod, M. (2021). Impact of reverberation through deep neural networks on adversarial perturbations. In 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA). IEEE.
   
• Bernhard, R., Moellic, P.A., Mermillod, M., Bourrier, Y., Cohendet, R., Solinas, M., & Reyboz, M. (2021). Impact of Spatial Frequency-Based Constraints on Adversarial Robustness. In 2021 IEEE International Joint Conference on Neural Networks (IJCNN).
   
• Solinas, M., Rousset, S., Cohendet, R., Bourrier, Y., Mainsant, M., Molnos, A., Reyboz, M., & Mermillod, M. (2021). Beneficial Effect of Combined Replay for Continual Learning. ICAART 2020—Proceedings of the 13th International Conference on Agents and Artificial Intelligence, Volume 2. 205–217.
   
• Solinas, M., Galiez, C., Cohendet, R., Rousset, S., Reyboz, M., & Mermillod, M. (2020). A universal property of autoencoders and its application to transfer learning. In 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA) (pp. 877–882). IEEE.
   
• Lacroix, A., Nalborczyk, L., Dutheil, F., Kovarski, K., Chokron, S., Garrido, M., Gomot, M., & Mermillod, M. (2021). High-spatial-frequency-filtered primes accelerate the categorization of happy faces in adults with autism. Brain and Cognition, 155, 105811.
   
• Entzmann, L., Guyader, N., Kauffmann, L., Lenouvel, J., Charles, C., Peyrin, C., ... & Mermillod, M. (2021). The Role of Emotional Content and Perceptual Saliency During the Programming of Saccades Toward Faces. Cognitive Science, 45(10), e13042.
   
• Park, G., Kim, H., Mermillod, M., & Thayer, J. F. (2021). The Modulation of Cardiac Vagal Tone on Attentional Orienting to Fair-Related Faces: Low HRV Is Associated with Faster Attentional Engagement to Fair-Relevant Stimuli. Cognitive, Affective, & Behavioral Neuroscience, 1–15.
   
• Bret, A., Beffara, B., Mierop, A., & Mermillod, M. (2021). Differentiated evaluation of counter-conditioned stimuli as a function of right-wing authoritarianism. Social Psychological Bulletin, 16(2), 1–26.
   
• Mermillod, M., & Morisseau, T. (2021). “Protect Others to Protect Myself: A Weakness of Western Countries in the Face of Current and Future Pandemics? Psychological and Neuroscientific Perspectives.” Frontiers in Integrative Neuroscience, 15, 8.
   
• Serole, C., Auclair, C., Prunet, D., Charkhabi, M., Lesage, F.X., Baker, J.S., Mermillod, M., Gerbaud, L., Dutheil, F. (2021). The Forgotten Health-Care Occupations at Risk of Burnout – A Survey on Burnout, Job Demand-Control-Support, and Effort-Reward Imbalance. Journal of Occupational and Environmental Medicine, 63 (7), e416–e425.
   
• Dutheil, F., Comptour, A., Morlon, R., Mermillod, M., Pereira, B., Baker, J. S., Charkhabi, M., Clinchamps, M., & Bourdel, N. (2021). Autism spectrum disorder and air pollution: a systematic review and meta-analysis. Environmental Pollution, 116856.
   
• Merlhiot, G., Mondillon, L., Méot, A., Dutheil, F., & Mermillod, M. (2021). Facial width-to-height ratio underlies perceived dominance in facial emotional expressions. Personality and Individual Differences, 172, 110583.
   
• Shankland, R., Favre, P., Kotsou, I., & Mermillod, M. (2021). Mindfulness and De-automatization: Effect of Mindfulness-Based Interventions on the Processing of Emotional Facial Expressions. Mindfulness, 12(1), 226–239.
   
• Clinchamps, M., Auclair, C., Prunet, D., Pfabigan, D., Lesage, F. X., Baker, J. S., Parreira, L., Mermillod, M., Gerbaud, L., & Dutheil, F. (2021). Burnout Among Hospital Non-Healthcare Staff: Influence of Job Demands, Control, Support, and Effort-Reward Imbalance. Journal of Occupational and Environmental Medicine, 63(1), e13-e20.