Oscillatory neural network learning for pattern recognition: an on-chip learning perspective and implementation

Autor: Madeleine Abernot, Nadine Azemard, Aida Todri-Sanial

Publikováno v: Frontiers in Neuroscience, Vol 17 (2023)

In the human brain, learning is continuous, while currently in AI, learning algorithms are pre-trained, making the model non-evolutive and predetermined. However, even in AI models, environment and input data change over time. Thus, there is a need t

Externí odkaz: https://doaj.org/article/8700435fae8f4c6d962dbc068c8c65ad

Simulation and implementation of two-layer oscillatory neural networks for image edge detection: bidirectional and feedforward architectures

Autor: Madeleine Abernot, Todri-Sanial Aida

Publikováno v: Neuromorphic Computing and Engineering, Vol 3, Iss 1, p 014006 (2023)

The growing number of edge devices in everyday life generates a considerable amount of data that current AI algorithms, like artificial neural networks, cannot handle inside edge devices with limited bandwidth, memory, and energy available. Neuromorp

Externí odkaz: https://doaj.org/article/ba4eb1cfb81a4bf1b6666ddf6523cf4d

SIFT-ONN: SIFT Feature Detection Algorithm Employing ONNs for Edge Detection

Autor: Madeleine Abernot, Sylvain Gauthier, Theophile Gonos, Aida Todri-Sanial

Publikováno v: NICE 2023-Neuro-Inspired Computational Elements Workshop
NICE 2023-Neuro-Inspired Computational Elements Workshop, Apr 2023, San Antonio, TX, United States. ⟨10.1145/3584954.3584999⟩
Proceedings of the 2023 Annual Neuro-Inspired Computational Elements Conference, NICE 2023, 100-107
STARTPAGE=100;ENDPAGE=107;TITLE=Proceedings of the 2023 Annual Neuro-Inspired Computational Elements Conference, NICE 2023

International audience; Mobile robot navigation tasks can be applied in various domains, such as in space, underwater, and transportation industries, among others. In navigation, robots analyze their environment from sensors and navigate safely up to

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::89371f6acada1b8c65a0850ecaaa721f
https://doi.org/10.1145/3584954.3584999

Oscillatory Neural Network for Edge Computing: A Mobile Robot Obstacle Avoidance Application

Autor: Madeleine Abernot, Hamza Amara, Thierry Gil, Aida Todri-Sanial

Publikováno v: 2022 IEEE International Conference on Metrology for Extended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE).

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::395e5548b99e2546b8fd69162f58ad74
https://doi.org/10.1109/metroxraine54828.2022.9967581

Oscillatory Neural Network as Hetero-Associative Memory for Image Edge Detection

Autor: Madeleine Abernot, Thierry Gil, Aida Todri-Sanial

Publikováno v: NICE 2022-9th Neuro-Inspired Computational Elements Workshop
NICE 2022-9th Neuro-Inspired Computational Elements Workshop, Mar 2022, New York (Virtual), United States. pp.13-21, ⟨10.1145/3517343.3517348⟩
Neuro-Inspired Computational Elements Conference

International audience; The increasing amount of data to be processed on edge devices, such as cameras, has motivated Artificial Intelligence (AI) integration at the edge. Typical image processing methods performed at the edge, such as feature extrac

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::709f9a4f758c2990b42f806880327a53
https://hal-lirmm.ccsd.cnrs.fr/lirmm-03586865/document