Juan Irving Vasquez

Robotics and Computer Vision Researcher

Deep Learning

This posgraduate course adresses the fundamentals of deep learning as well as the recent architectures and applictions.

Content

  1. Background review
  2. Introduction
    1. Machine learning review
    2. Machine learning tasks
    3. Machine learning types
    4. Deep learning first view
      IRN_Intro_machine_learning
  3. Neural networks review
    1. Multilayer perceptron
    2. Deep Neural Networks
    3. Feedforward deep networks
    4. Gradient descent
    5. Backpropagation algorithm
    6. Regularization methods
  4. Hyperparameters tunning
    1. Practial aspects
    2. Design of experiments
    3. Error analysis
    4. Validation metrics
  5. Convolutional Neural Networks
    1. Cross correlation
    2. Convolutional neural networks
    3. Selected architectures
  6. Autoencoders
    1. Unsupervised learning
    1. Principal components analysis
    2. Undercomplete autoencoders
    3. Variational autoencoders
  7. Recurrent Neural Networks
  8. Generative Adversarial Network
  9. Transformers

Bibliografía

  • Ian Goodfellow Yoshua, Bengio Aaron Courville, 2016, Deep learning, www.deeplearningbook.org
  • Nikhil Buduma, Nicholas Lacascio, 2017, Fundamentals of Deep Learning. Published by O’Reilly Media.
  • Marvin, M., & Seymour, A. P. (1969). Perceptrons. Cambridge, MA: MIT Press6, 318-362.
  • Norvig, P., & Russell, S. (2004). Inteligencia Artificial. Un Enfoque Moderno. Phh Pretice Hall, Mexico.
A %d blogueros les gusta esto: