Name: Xavier Hinaut
Type: User
Company: INRIA / IMN / LaBRI
Bio: Inria research scientist & Reservoir activist, bio-inspired AI, computational neuroscience, cognitive robotics
Twitter: neuronalX
Location: Bordeaux, France
Blog: http://www.xavierhinaut.com
Xavier Hinaut's Projects
Agency Theme for Jekyll
A generative network for animal vocalizations. For dimensionality reduction, sequencing, clustering, corpus-building, and generating novel 'stimulus spaces'. All with notebook examples using freely available datasets.
Code and supplementary informations for the ICANN 2024 conference paper
Generating birdsong with WaveNet
Routines for data handling in a bout annotation project
Scripts to evaluate canapy for journal paper
Vocal learning model with RNN Decoder and Low-dimensional GAN Generator
Provide Semantic Parsing solutions and Natural Language Inferences for multiple languages following the idea of the syntax-semantics interface.
Site web du coglab bordelais.
Materiel pour le cours de deep learning pour le master de sciences cognitives (2018)
Prediction on COVID-19 variables (nr of cases, new cases, cured, ...) with Recurrent Neural Networks (RNNs)
Cross-Situational Learning with Bayesian Generative Models for Multimodal Category and Word Learning in Robots
Datas from lucid dream survey
Conference paper and supplementary material of Dinh & Hinaut, ICANN 2020.
Neural network model for chunking written in Python 3.
Recurrent Neural Network for Syntax Learning with Flexible Representations for Robotic Architectures
EchoZic : projet de sonification de Reservoirs - Hackathon Hack1robo ร Cap Sciences les 9-11 Fรฉvrier 2024
Scripts and utilities for processing electrophysiology data
Code for the paper "Evolving Reservoirs for Meta Reinforcement Learning"
Training neural language models based on Echo State Networks with different readout functions.
A robust model of gated graded working memory
Meta-Learning through Hebbian Plasticity in Random Networks: https://arxiv.org/abs/2007.02686
Xavier Hinaut's academic website