"A little learning is a dangerous thing; drink deep, or taste not the Pierian spring: there shallow draughts intoxicate the brain, and drinking largely sobers us again."
- Ulises Moya Sánchez, BSC/UAG
- Ulises Cortés, BSC
This course presents an introduction of the bases and practices of Deep Learning (DL). We will focus in Convolutional Neural Networks for image classification in large datasets in the hands-on session.
- Introduction to Neural networks and Deep Learning.
- Understand the relations and differences between shallow and deep nets.
- Main characteristics and DL net selection (Boltzmann machines, convolutional nets, recurrent nets).
- Application and use cases of DL methods.
- Convolutional neural networks application: CNN architectures, Training, fine tuning and regularization (Hands on session)
- Parallel computing tools for DL (Data augmentation)
- DL limitations (noise, size, overfitting).
Ian Goodfellow and Yoshua Bengio and Aaron Courville
MIT Press 2016
Keras (as wrapper) on TensorFlow