Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
portfolio
Stereo depth estimation from the StereoSpike SNN model (MVSEC dataset)
Model inference demonstration 
DeepSTRF: a PyTorch library for sensory neural response modeling with deep neural networks
Repository URL: https://github.com/urancon/deepSTRF
publications
StereoSpike: Depth Learning With a Spiking Neural Network
Published in IEEE Access, 2022
Stereo depth estimation from event cameras with a SNN
Recommended citation: Rançon et al. (2022). "StereoSpike: Depth Learning with a Spiking Neural Network." IEEE Access; doi: 10.1109/ACCESS.2022.3226484
Download Paper
Optical flow estimation from event-based cameras and spiking neural networks
Published in Frontiers in Neuroscience, 2023
Optic flow regression from even-based cameras with SNNs on MVSEC and DSEC datasets
Recommended citation: Cuadrado et al. (2023). "Optical flow estimation from event-based cameras and spiking neural networks." Frontiers in Neuroscience; doi: https://doi.org/10.3389/fnins.2023.1160034
Download Paper
FPGA implementation of a Spiking Neural Network for Real-Time Action Potential and Burst Detection
Published in 2023 IEEE Biomedical Circuits and Systems Conference (BioCAS), 2023
Neuromorphic hardware implementation of an SNN for real-time online spike detection from micro-electrode array electrophysiology data
Recommended citation: Cheslet et al. (2023). "FPGA implementation of a Spiking Neural Network for Real-Time Action Potential and Burst Detection." BioCAS; doi: 10.1109/BioCAS58349.2023.10388622
Download Paper
A general model unifying the adaptive, transient and sustained properties of ON and OFF auditory neural responses
Published in PLoS Computational Biology, 2024
Augmenting and benchmarking models of auditory neural responses on various datasets
Recommended citation: Rançon et al. (2024). "A general model unifying the adaptive, transient and sustained properties of ON and OFF auditory neural responses." PLoS Computational Biology; doi: https://doi.org/10.1371/journal.pcbi.1012288
Download Paper
A 23.5 TOPS/W Depthwise Separable Convolution Accelerator for Event-based Depth Estimation
Published in 2025 IEEE International Symposium on Circuits and Systems (ISCAS), 2025
Energy- and area-efficient hardware accelerator for depthwise separable convolutions, applied to event-based depth estimation
Recommended citation: Brito et al. (2025). "A 23.5 TOPS/W Depthwise Separable Convolution Accelerator for Event-based Depth Estimation." ISCAS; doi: 10.1109/ISCAS56072.2025.11044178
Download Paper
DelRec: learning delays in recurrent spiking neural networks
Published in arXiv, 2025
An efficient algorithm to learn delays in recurrent spiking neural networks with surrogate gradients
Recommended citation: Quéant et al. (2025). "DelRec: learning delays in recurrent spiking neural networks." ArXiv; doi: https://doi.org/10.48550/arXiv.2509.24852
Download Paper
Temporal recurrence as a general mechanism to explain neural responses in the auditory system
Published in Communications Biology, 2025
Using and reverse-engineering deep gated RNNs as auditory neural response models
Recommended citation: Rançon et al. (2025). "Temporal recurrence as a general mechanism to explain neural responses in the auditory system." Communications Biology, 8, 1456; doi: 10.1038/s42003-025-08858-3
Download Paper
Dreaming up scale invariance via inverse renormalization group
Published in Physical Review E, 2026
Using a minimal machine learning model to generate plausible 2d Ising configurations at criticality
Recommended citation: Rançon, A., Rançon, U., Ivek, T., & Balog, I. (2026). "Dreaming up scale invariance via inverse renormalization group." Physical Review E, 113(5), 055302; doi: 10.1103/3njc-5tlx
Download Paper
talks
teaching
Managing an Arduino project
Undergraduate course, Bordeaux University Technical Institute (IUT), Department of Electrical Engineering (GEII), 2021
Teaching 1st year students programming in Arduino, and guiding them on a personal hands-on project of their choice.
Introduction to Spiking Neural Networks
Graduate course, University of Toulouse (Paul Sabatier), Master of neuroscience, 2024
Introductory course on low-level modeling of the brain with spiking neural networks (SNNs).