|
Docente
|
GASPARETTI FABIO
(programma)
Introduzione al Deep Learning; Addestramento di architetture Deep: tecniche di hyperparameter tuning, batch normalization, faster optimizers, regularization per reti deep; Convolutional Neural Networks (CNN/ConvNets); Analisi di sequenze: Recurrent Neural Networks (GRU, LSTM, Bidirectional); Architetture Encoder-Decoder, Autoencoders, Variational Autoencoders; Attention layers ; Generative Adversarial Networks (GAN); Deep Reinforcement Learning; Embeddings; Principali architetture convolutive (AlexNet, VGG, NiN, GoogLeNet/Inception, ResNet, DenseNet); Applicazioni alla Computer Vision e all'Analisi del linguaggio naturale in linguaggio Keras
(testi)
Hands-on machine learning with Scikit-learn Keras and TensorFlow by Aurelion Geron published by O` Reilley
Deep Learning by Ian Goodfellow, Yoshua Bengio and Aaron Courville published by MIT Press
|
Università Roma Tre