Paired competing neurons improving STDP supervised local learning in Spiking Neural Networks

Autor: Gaspard Goupy, Pierre Tirilly, Ioan Marius Bilasco

Publikováno v: Frontiers in Neuroscience, Vol 18 (2024)

Direct training of Spiking Neural Networks (SNNs) on neuromorphic hardware has the potential to significantly reduce the energy consumption of artificial neural network training. SNNs trained with Spike Timing-Dependent Plasticity (STDP) benefit from

Externí odkaz: https://doaj.org/article/715120ed573f40e58770dbd2716b9311

Facial Landmark Detection with Spatio‐temporal Modeling

Autor: Romain BELMONTE, Pierre TIRILLY, Ioan Marius BILASCO, Nacim IHADDADENE, Chaabane DJERABA

Publikováno v: Face Analysis Under Uncontrolled Conditions. :93-131

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::570de39ad56e6e68cf624d41349724f1
https://doi.org/10.1002/9781394173853.ch3

Conclusion to Part 1

Autor: Romain BELMONTE, Pierre TIRILLY, Ioan Marius BILASCO, Nacim IHADDADENE, Chaabane DJERABA

Publikováno v: Face Analysis Under Uncontrolled Conditions. :133-145

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::7a6b08c52a9cda5a8c858c5a2a6155f3
https://doi.org/10.1002/9781394173853.oth1

A Study On the Effects of Pre-processing On Spatio-temporal Action Recognition Using Spiking Neural Networks Trained with STDP

Autor: Pierre Tirilly, Ioan Marius Bilasco, Mireille El-Assal

Publikováno v: CBMI
2021 Content-based Multimedia Indexing
Content-based Multimedia Indexing
Content-based Multimedia Indexing, Jun 2021, Lille (en ligne), France

International audience; There has been an increasing interest in spiking neural networks in recent years. SNNs are seen as hypothetical solutions for the bottlenecks of ANNs in pattern recognition, such as energy efficiency. But current methods such

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1c9d70847570c15e5c7ab726bca3e67c

Unsupervised visual feature learning with spike-timing-dependent plasticity: How far are we from traditional feature learning approaches?

Autor: Ioan Marius Bilasco, Pierre Falez, Pierre Tirilly, Pierre Boulet, Philippe Devienne

Publikováno v: Pattern Recognition
Pattern Recognition, Elsevier, 2019, 93, pp.418-429. ⟨10.1016/j.patcog.2019.04.016⟩
Pattern Recognition, 2019, 93, pp.418-429. ⟨10.1016/j.patcog.2019.04.016⟩

Spiking neural networks (SNNs) equipped with latency coding and spike-timing dependent plasticity rules offer an alternative to solve the data and energy bottlenecks of standard computer vision approaches: they can learn visual features without super

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0b68a46f201fb3a28a7bc4d3cc3a65ff
https://hal.archives-ouvertes.fr/hal-02146284/file/S0031320319301621.pdf