[{"command":"insert","method":null,"selector":".course-modal-ajax-placeholder-967511","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  Advances in Machine Vision\n\u003C\/h2\u003E\n                  \u003Cdiv class=\u0022field-spacing\u0022\u003E\n        \u003Cdiv class=\u0022field__label h3 dash\u0022\u003EECTS :\n          3\n        \u003C\/div\u003E\n      \u003C\/div\u003E\n                  \u003Cdiv class=\u0022field-spacing\u0022\u003E\n        \u003Cdiv class=\u0022field__label h3 dash\u0022\u003ESemester:\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\u003ELecture:\u003C\/span\u003E\n                                      \u003Cspan\u003E12\u003C\/span\u003E\n                      \u003C\/div\u003E\n                                \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                          \u003Cspan class=\u0022field__label h4 mt-5 \u0022\u003EPractical study :\u003C\/span\u003E\n                                      \u003Cspan\u003E12\u003C\/span\u003E\n                      \u003C\/div\u003E\n                                \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                          \u003Cspan class=\u0022field__label h4 mt-5 \u0022\u003EDirected study:\u003C\/span\u003E\n                                      \u003Cspan\u003E12\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\u003EAnglais\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\u003EProgramme \/ plan \/ contenus\u003C\/div\u003E\n                        \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                                      \u003Cspan\u003E\u003Cp\u003E1. Overview of Advanced ML\u003C\/p\u003E\n\u003Cp\u003ERecap of supervised learning and neural network fundamentals\u003C\/p\u003E\n\u003Cp\u003EMotivation for deep learning: hierarchical feature learning\u003C\/p\u003E\n\u003Cp\u003EGPU computing and modern frameworks (TensorFlow, PyTorch)\u003C\/p\u003E\n\u003Cp\u003E2. Deep Feedforward Networks\u003C\/p\u003E\n\u003Cp\u003EArchitecture and training of deep networks\u003C\/p\u003E\n\u003Cp\u003EActivation functions, normalization layers, dropout\u003C\/p\u003E\n\u003Cp\u003EOptimization: gradient descent variants, learning rate scheduling\u003C\/p\u003E\n\u003Cp\u003E3. Convolutional Neural Networks (CNNs)\u003C\/p\u003E\n\u003Cp\u003EConvolutional layers, pooling, and feature maps\u003C\/p\u003E\n\u003Cp\u003EClassical architectures: LeNet, AlexNet, VGG, ResNet\u003C\/p\u003E\n\u003Cp\u003EApplications in vision: classification, detection, segmentation\u003C\/p\u003E\n\u003Cp\u003E4. Recurrent and Sequence Models\u003C\/p\u003E\n\u003Cp\u003ERecurrent Neural Networks (RNN), LSTM, GRU\u003C\/p\u003E\n\u003Cp\u003EAttention mechanisms and sequence-to-sequence models\u003C\/p\u003E\n\u003Cp\u003EApplications: speech recognition, time-series forecasting, NLP\u003C\/p\u003E\n\u003Cp\u003E5. Transformer Architecture and Large Language Models (LLMs)\u003C\/p\u003E\n\u003Cp\u003EThe Transformer: self-attention, multi-head attention, positional encoding\u003C\/p\u003E\n\u003Cp\u003EPre-training and fine-tuning paradigms\u003C\/p\u003E\n\u003Cp\u003EOverview of major LLMs (BERT, GPT family, T5)\u003C\/p\u003E\n\u003Cp\u003EPrompt engineering and transfer learning concepts\u003C\/p\u003E\n\u003Cp\u003E6. Generative Deep Learning\u003C\/p\u003E\n\u003Cp\u003EAutoencoders and Variational Autoencoders (VAEs)\u003C\/p\u003E\n\u003Cp\u003EGenerative Adversarial Networks (GANs)\u003C\/p\u003E\n\u003Cp\u003EDiffusion models (intro and applications)\u003C\/p\u003E\n\u003Cp\u003E7. Modern Techniques \u0026amp; Trends\u003C\/p\u003E\n\u003Cp\u003ESelf-supervised and contrastive learning\u003C\/p\u003E\n\u003Cp\u003EFoundation models and multi-modal learning\u003C\/p\u003E\n\u003Cp\u003EEfficient training: pruning, quantization, model compression\u003C\/p\u003E\n\u003Cp\u003E8. Evaluation \u0026amp; Ethics\u003C\/p\u003E\n\u003Cp\u003EEvaluation of deep learning models (accuracy, robustness, interpretability)\u003C\/p\u003E\n\u003Cp\u003EBias, fairness, and ethical considerations in AI\u003C\/p\u003E\n\u003Cp\u003EResponsible deployment and environmental cost of large models\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 Continue non Int\u00e9grale\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}]