Provide advanced and specific skills in Deep neural networks. The course consists of a theoretical part on the fundamental concepts, and laboratory activities in which these concepts are applied and developed through a software framework. At the end of the course the student will be able to: adequately train and optimize Deep neural networks; distinguish between different solutions and be able to choose and customize the most effective architectures in real-world scenarios, supervised, unsupervised or following a reinforcement learning approach.
Curriculum
teacher profile teaching materials
“Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems”, O'Reilly Media, Inc, USA, 2019.
Programme
Introduction to DL; Training of Deep Architecture: hyperparameter tuning, batch normalization, faster optimizers, regularization ; Convolutional Neural Networks (CNN/ConvNets); Recurrent Neural Networks (GRU, LSTM, Bidirectional); Encoder-Decoder, Autoencoders, Variational Autoencoders; Attention layers ; Generative Adversarial Networks (GAN); Deep Reinforcement Learning; Embeddings; Use cases: AlexNet, VGG, NiN, GoogLeNet/Inception, ResNet, DenseNet; Use cases: Computer Vision and NLPCore Documentation
Simon J.D. Prince. "Understanding Deep Learning". MIT Press Dec 5th 2023 A. Geron,“Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems”, O'Reilly Media, Inc, USA, 2019.
Type of evaluation
The assessment is based on tests taken during the course and a final exam. The ongoing tests allow the student to take a shorter final exam. All the tests are written examinations, and consist of open-ended and closed-ended questions. teacher profile teaching materials
“Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems”, O'Reilly Media, Inc, USA, 2019.
Programme
Introduction to DL; Training of Deep Architecture: hyperparameter tuning, batch normalization, faster optimizers, regularization ; Convolutional Neural Networks (CNN/ConvNets); Recurrent Neural Networks (GRU, LSTM, Bidirectional); Encoder-Decoder, Autoencoders, Variational Autoencoders; Attention layers ; Generative Adversarial Networks (GAN); Deep Reinforcement Learning; Embeddings; Use cases: AlexNet, VGG, NiN, GoogLeNet/Inception, ResNet, DenseNet; Use cases: Computer Vision and NLPCore Documentation
Simon J.D. Prince. "Understanding Deep Learning". MIT Press Dec 5th 2023 A. Geron,“Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems”, O'Reilly Media, Inc, USA, 2019.
Type of evaluation
The assessment is based on tests taken during the course and a final exam. The ongoing tests allow the student to take a shorter final exam. All the tests are written examinations, and consist of open-ended and closed-ended questions. teacher profile teaching materials
“Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems”, O'Reilly Media, Inc, USA, 2019.
Programme
Introduction to DL; Training of Deep Architecture: hyperparameter tuning, batch normalization, faster optimizers, regularization ; Convolutional Neural Networks (CNN/ConvNets); Recurrent Neural Networks (GRU, LSTM, Bidirectional); Encoder-Decoder, Autoencoders, Variational Autoencoders; Attention layers ; Generative Adversarial Networks (GAN); Deep Reinforcement Learning; Embeddings; Use cases: AlexNet, VGG, NiN, GoogLeNet/Inception, ResNet, DenseNet; Use cases: Computer Vision and NLPCore Documentation
Simon J.D. Prince. "Understanding Deep Learning". MIT Press Dec 5th 2023 A. Geron,“Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems”, O'Reilly Media, Inc, USA, 2019.
Type of evaluation
The assessment is based on tests taken during the course and a final exam. The ongoing tests allow the student to take a shorter final exam. All the tests are written examinations, and consist of open-ended and closed-ended questions.