Βαθιά Μάθηση

Deep Learning Course Syllabus

  • Neural Networks, Multi Layer Perceptrons (back-prop), R-prop, Extreme Learning Machines (no-prop)
  • Deep Neural Networks
  • Loss function, Hyperparameter tuning, Regularization, Model selection, weight decay, dropout, Optimization (adam, rmsprop), Ensemble, bagging, boosting
  • Convolutional Neural Networks (CNN), LeNet/AlexNet, Deep Residual Networks (ResNet). Application of CNNs to Single-Image Super-Resolution
  • CNN variations and other solutions for object detection: R-CNN, Fast R-CNN, Faster R-CNN, Mask R-CNN, SSD, YOLO
  • Recurrent Neural Networks, Long Short-Term Memory Networks, Gated Recurrent Units.
  • Transformers, sequence-to-sequence (seq2seq) learning, attention
  • Generative Models. Restricted Boltzman Machines, Deep Boltzman Machines, Deep Belief Networks). Autoencoders, Stacked (Denoising AutoEncoders), Variational Autoencoders. Generative Adversarial Networks.
  • Transfer learning, domain adaptation.
  • Tensor-based learning, tensor decomposition.
  • Reinforcement Learning
  • Explainability, fairness and transparency in Machine Learning / Deep Learning.