/DeepLearningfromScratch2018

DeepLearningfromScratch2018

Primary LanguageJupyter NotebookMIT LicenseMIT

Deep Learning from Scratch (v3.0)

This course is organized by the DataScienceGroup@UB (http://datascience.barcelona/)

Deep learning is one of the fastest growing areas of machine learning and a hot topic in both academia and industry. This course will cover the basics of deep learning by using a hands-on approach.

Course Agenda

Day 1

  • Introduction to Deep Learning and its applications. Using the Jupyter notebook & Docker.
  • Basic Concepts: Score & Loss functions, Optimization (SGD), Linear Regression.
  • Automated differentiation, Backpropagation, Training a Neural Netwotk from Scratch.
  • Tensorflow programming model. Keras.

    Day2

  • Recap Exercise
  • Convolutions & CNN models.
  • Recurrent Neural Netwoks.
  • Unsupervised Learning.
  • Advanced Applications.