[{"command":"insert","method":null,"selector":".course-modal-ajax-placeholder-956172","data":"\u003Cdiv class=\u0022container content-rte\u0022\u003E\n  \u003Cdiv class=\u0022row\u0022\u003E\n    \u003Cdiv class=\u0022box col-md-6 bg-primary text-white\u0022\u003E\n      \u003Ch2 class=\u0022h1 text-left\u0022\u003E  Apprentissage profond\n\u003C\/h2\u003E\n                  \u003Cdiv class=\u0022field-spacing\u0022\u003E\n        \u003Cdiv class=\u0022field__label h3 dash\u0022\u003EECTS :\n          2.5\n        \u003C\/div\u003E\n      \u003C\/div\u003E\n                  \u003Cdiv class=\u0022field-spacing\u0022\u003E\n        \u003Cdiv class=\u0022field__label h3 dash\u0022\u003ESemestre calendaire :\n          Semestre 1\n        \u003C\/div\u003E\n      \u003C\/div\u003E\n            \u003Cdiv class=\u0022field-spacing\u0022\u003E\n      \u003Cdiv class=\u0022field__label h3 dash\u0022\u003ED\u00e9tail du volume horaire\u003C\/div\u003E\n                        \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                          \u003Cspan class=\u0022field__label h4 mt-5 \u0022\u003ECours magistraux :\u003C\/span\u003E\n                                      \u003Cspan\u003E18\u003C\/span\u003E\n                      \u003C\/div\u003E\n                                                                                        \u003C\/div\u003E\n        \u003Cdiv class=\u0022field-spacing\u0022\u003E\n      \u003Cdiv class=\u0022field__label h3 dash\u0022\u003ELangue d\u0026#039;enseignement\u003C\/div\u003E\n                        \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                                      \u003Cspan\u003EFran\u00e7ais\u003C\/span\u003E\n                      \u003C\/div\u003E\n                  \u003C\/div\u003E\n        \u003Cdiv class=\u0022field-spacing\u0022\u003E\n      \u003Cdiv class=\u0022field__label h3 dash\u0022\u003EEnseignement \u00e0 distance\u003C\/div\u003E\n                        \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                                      \u003Cspan\u003Enon\u003C\/span\u003E\n                      \u003C\/div\u003E\n                  \u003C\/div\u003E\n      \u003C\/div\u003E\n    \u003Cdiv class=\u0022box col-md-6\u0022\u003E\n            \u003Cdiv class=\u0022field-spacing\u0022\u003E\n      \u003Cdiv class=\u0022field__label h3 dash\u0022\u003EPr\u00e9requis\u003C\/div\u003E\n                        \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                                      \u003Cspan\u003E\u003Cp\u003EBases d\u2019apprentissage automatique\u003C\/p\u003E\u003C\/span\u003E\n                      \u003C\/div\u003E\n                  \u003C\/div\u003E\n        \u003Cdiv class=\u0022field-spacing\u0022\u003E\n      \u003Cdiv class=\u0022field__label h3 dash\u0022\u003EProgramme \/ plan \/ contenus\u003C\/div\u003E\n                        \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                                      \u003Cspan\u003E\u003Cp\u003EL\u2019apprentissage profond (deep learning) constitue aujourd\u2019hui une composante essentielle de l\u2019intelligence artificielle (IA).\u003Cbr\u003E\nIl s\u2019agit d\u2019un ensemble de m\u00e9thodes permettant de mod\u00e9liser des donn\u00e9es complexes \u00e0 un haut niveau d\u2019abstraction,\u003Cbr\u003E\n\u00e0 l\u2019aide de r\u00e9seaux de neurones artificiels compos\u00e9s de multiples couches.\u003C\/p\u003E\n\u003Cp\u003ECes approches ont permis des progr\u00e8s spectaculaires dans des domaines vari\u00e9s tels que :\u003Cbr\u003E\n- la vision par ordinateur (reconnaissance d\u2019images, d\u00e9tection d\u2019objets, vision autonome),\u003Cbr\u003E\n- le traitement automatique du langage naturel (traduction, g\u00e9n\u00e9ration de texte, mod\u00e8les comme ChatGPT ou DeepSeek),\u003Cbr\u003E\n- la reconnaissance vocale et sonore,\u003Cbr\u003E\n- ou encore la g\u00e9n\u00e9ration de contenu multim\u00e9dia (images, musique, vid\u00e9os). \u0026nbsp;\u003C\/p\u003E\n\u003Cp\u003EProgramme du cours\u003C\/p\u003E\n\u003Cp\u003EIntroduction \u00e0 l\u2019apprentissage profond:\u003Cbr\u003E\n- Motivation et \u00e9mergence du deep learning\u003Cbr\u003E\n- R\u00e9seaux de neurones artificiels (ANN)\u003Cbr\u003E\n- Neurone artificiel, fonctions d\u2019activation\u003Cbr\u003E\n- Propagation avant et r\u00e9tropropagation du gradient\u003Cbr\u003E\n- Optimisation et r\u00e9gularisation\u003C\/p\u003E\n\u003Cp\u003ER\u00e9seaux de neurones convolutifs (CNN)\u003Cbr\u003E\n\u0026nbsp;- Convolutions, pooling, architectures classiques (LeNet, AlexNet, ResNet)\u003Cbr\u003E\n\u0026nbsp;- Applications \u00e0 la vision par ordinateur\u003C\/p\u003E\n\u003Cp\u003EMod\u00e8les g\u00e9n\u00e9ratifs\u003Cbr\u003E\n- Auto-encodeurs et variantes (variational auto-encoders, denoising auto-encoders)\u003Cbr\u003E\n- R\u00e9seaux antagonistes g\u00e9n\u00e9ratifs (GAN)\u003C\/p\u003E\n\u003Cp\u003EArchitectures avanc\u00e9es\u003Cbr\u003E\n\u0026nbsp;- R\u00e9seaux r\u00e9currents (RNN, LSTM, GRU)\u003Cbr\u003E\n\u0026nbsp;- Transformers et mod\u00e8les de langage \u00e0 grande \u00e9chelle (LLMs)\u003Cbr\u003E\n\u0026nbsp;- Vision Transformers (ViT), diffusion models\u003C\/p\u003E\n\u003Cp\u003EOutils et biblioth\u00e8ques logicielles\u003Cbr\u003E\n\u0026nbsp;- Graphes de calcul\u003Cbr\u003E\n\u0026nbsp;- Pr\u00e9sentation et prise en main de TensorFlow, PyTorch et Keras\u003C\/p\u003E\u003C\/span\u003E\n                      \u003C\/div\u003E\n                  \u003C\/div\u003E\n        \u003Cdiv class=\u0022field-spacing\u0022\u003E\n      \u003Cdiv class=\u0022field__label h3 dash\u0022\u003EObjectifs d\u0026#039;apprentissage\u003C\/div\u003E\n                        \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                                      \u003Cspan\u003E\u003Cp\u003E\u00c0 l\u2019issue du cours, les \u00e9tudiants seront capables de :\u003Cbr\u003E\n- Comprendre les principes fondamentaux de l\u2019apprentissage profond et des r\u00e9seaux de neurones.\u003Cbr\u003E\n- Concevoir, entra\u00eener et \u00e9valuer des mod\u00e8les adapt\u00e9s \u00e0 diff\u00e9rents types de donn\u00e9es.\u003Cbr\u003E\n- Identifier les architectures avanc\u00e9es et leurs applications sp\u00e9cifiques (vision, texte, audio, etc.).\u003Cbr\u003E\n- Utiliser les principales biblioth\u00e8ques logicielles (TensorFlow, PyTorch, Keras) pour la mise en \u0153uvre pratique de mod\u00e8les de deep learning.\u003C\/p\u003E\u003C\/span\u003E\n                      \u003C\/div\u003E\n                  \u003C\/div\u003E\n                                \u003Cdiv class=\u0022field-spacing\u0022\u003E\n      \u003Cdiv class=\u0022field__label h3 dash\u0022\u003EBibliographie\u003C\/div\u003E\n                        \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                                      \u003Cspan\u003E\u003Cp\u003EBengio, Y., Goodfellow, I., \u0026amp; Courville, A. (2017). Deep learning (Vol. 1). Cambridge,\u003Cbr\u003E\nMA, USA : MIT press. \u003Ca rel=\u0022nofollow noopener noreferrer\u0022 target=\u0022_blank\u0022 href=\u0022https:\/\/www.deeplearningbook.org\/\u0022\u003Ehttps:\/\/www.deeplearningbook.org\/\u003C\/a\u003E\u003C\/p\u003E\n\u003Cp\u003EG\u00e9ron, A. (2019). Hands-on machine learning with Scikit-Learn, Keras, and\u003Cbr\u003E\nTensorFlow : Concepts, tools, and techniques to build intelligent systems. O\u2019Reilly\u003Cbr\u003E\nMedia, Inc.\u003C\/p\u003E\n\u003Cp\u003EMallat, S. (2018) Lecon inaugurale en sciences des donn\u00e9es au coll\u00e8ge de France.\u003Cbr\u003E\n\u003Ca rel=\u0022nofollow noopener noreferrer\u0022 target=\u0022_blank\u0022 href=\u0022https:\/\/www.college-de-france.fr\/fr\/agenda\/lecon-inaugurale\/sciences-des-donnees\/sciences-des-donnees\u0022\u003Ehttps:\/\/www.college-de-france.fr\/fr\/agenda\/lecon-inaugurale\/sciences-des-donnees\/sciences-des-donnees\u003C\/a\u003E\u003C\/p\u003E\n\u003Cp\u003EFourer, D. et al. Site internet de l\u0027axe IA du laboratoire IBISC : \u003Ca rel=\u0022nofollow noopener noreferrer\u0022 target=\u0022_blank\u0022 href=\u0022https:\/\/ia.fourer.fr\/\u0022\u003Ehttps:\/\/ia.fourer.fr\/\u003C\/a\u003E\u003C\/p\u003E\u003C\/span\u003E\n                      \u003C\/div\u003E\n                  \u003C\/div\u003E\n        \u003Cdiv class=\u0022field-spacing\u0022\u003E\n      \u003Cdiv class=\u0022field__label h3 dash\u0022\u003ENature de l\u0026#039;\u00e9valuation\u003C\/div\u003E\n                        \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                                      \u003Cspan\u003EEvaluation Terminale\u003C\/span\u003E\n                      \u003C\/div\u003E\n                  \u003C\/div\u003E\n      \u003C\/div\u003E\n  \u003C\/div\u003E\n\u003C\/div\u003E\n","settings":null}]