Giter VIP home page Giter VIP logo

deeplearningfromscratch's Introduction

Deep Learning from Scratch

This course is organized by the Data Science Group @ UB

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

  • 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.
  • Convolutions & CNN models.
  • Recurrent Neural Netwoks.
  • Unsupervised Learning.
  • Advanced Applications: Neural art, colorization, music generation.

    Course Software Installation

    The best way to run the course software is to use a Docker container. There’s full documentation on installing Docker at docker.com, but in a few words, the steps are:

    • Go to docs.docker.com in your browser.
    • Step one of the instructions sends you to download the Docker Toolbox.
    • On the Toolbox page, click on the Mac/Windows download button.
    • Run that downloaded file to install the Toolbox.
    • At the end of the install process, chose the Docker Quickstart Terminal.
    • This opens up a new terminal window that runs through an installation script.
    • At the end of the script, you will see ASCII art of a whale and your are left at a prompt.
    • Run this command in the terminal: docker run hello-world
    • This will give you output confirming your installation of docker has worked: Hello from Docker
    • In the docker terminal, run (This operation requires a good internet connection to download ~2.5Gb; it will take some minutes): docker pull deepub/deepub
    • Run the DeepUB image on your system: docker run -i -t -p 8888:8888 deepub/deepub
    • Once these steps have been done, you can check the installation by starting your web browser and introducing this URL: http://localhost:8888 (or http://<DOCKER-MACHINE-IP>:8888 if you are using a Docker Machine VM) to access to the fully operational Jupyter notebook of this course. (Note: the address of your Docker Machine VM is printed at the end of the Docker booting process, just after the ASCII whale).

    Docker Optimization

    (Source: https://petewarden.com/2016/02/28/tensorflow-for-poets/)

    Under the hood, Docker actually uses VirtualBox to run its images, and we’ll use its control panel to manage the setup. To do that, we’ll need to take the following steps:

    • Find the VirtualBox application on your Mac/PC.
    • Once VirtualBox is open, you should see a left-hand pane showing virtual machines. There should be one called default that’s running.
    • Right-click on default to bring up the context menu and chose Close->ACPI Shutdown. The other close options should also work, but this is the most clean.
    • Once the shutdown is complete, default should have the text Powered off below it. Right click on it again and choose Settings… from the menu.
    • Click on the System icon, and then choose the Motherboard tab.
    • Drag the Base Memory slider as far as the green section goes, which is normally around 75% of your total laptop’s memory.
    • Click on the Processor tab, and set the number of processors higher than the default of 1.
    • Click OK on the settings dialog.
    • Right-click on default and choose Start->Headless Start.
  • deeplearningfromscratch's People

    Contributors

    algorismes avatar axelbrando avatar blauigris avatar gpascualg avatar oriolpujol avatar ssegui avatar

    Watchers

     avatar  avatar

    Recommend Projects

    • React photo React

      A declarative, efficient, and flexible JavaScript library for building user interfaces.

    • Vue.js photo Vue.js

      🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

    • Typescript photo Typescript

      TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

    • TensorFlow photo TensorFlow

      An Open Source Machine Learning Framework for Everyone

    • Django photo Django

      The Web framework for perfectionists with deadlines.

    • D3 photo D3

      Bring data to life with SVG, Canvas and HTML. 📊📈🎉

    Recommend Topics

    • javascript

      JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

    • web

      Some thing interesting about web. New door for the world.

    • server

      A server is a program made to process requests and deliver data to clients.

    • Machine learning

      Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

    • Game

      Some thing interesting about game, make everyone happy.

    Recommend Org

    • Facebook photo Facebook

      We are working to build community through open source technology. NB: members must have two-factor auth.

    • Microsoft photo Microsoft

      Open source projects and samples from Microsoft.

    • Google photo Google

      Google ❤️ Open Source for everyone.

    • D3 photo D3

      Data-Driven Documents codes.