Skip to content

Latest commit

 

History

History
34 lines (24 loc) · 2.71 KB

README.md

File metadata and controls

34 lines (24 loc) · 2.71 KB
Raw

This repository contains my solution of software labs for MIT 6.S191: Introduction to Deep Learning. All lecture slides and videos are available on the course website. They have wonderfully illustrated with diagrams and code which can be even understood by people just starting out Deep Learning. Course Website : www.introtodeeplearning.com

Please feel free to view through as I learn the basics of Deep Learning and the start of my journey through this subject.

WHY THIS COURSE

In a world that becomes evermore driven by data, just knowing how to program is becoming less and less sufficient. Industry leaders now not only need to understand the data they output but must also have a firm grasp of mathematics, specifically statistics, to prevent being fooled. Again and again we see world leaders, CEO, and the everyday man be made a fool of and lied to by misleading figures and emotions. Big Data has taken part in our lives and we must learn how to work with it rather than be overwhelmed by it. At least, that is the way I see it. One of the main minimal skills to have, is to understand how to get value out of data: the use of Deep Learning.

Opening the labs in Google Colaboratory:

The 2020 6.S191 labs will be run in Google's Colaboratory, a Jupyter notebook environment that runs entirely in the cloud, you don't need to download anything. To run these labs, you must have a Google account.

On this Github repo, navigate to the lab folder you want to run (lab1, lab2, lab3) and open the appropriate python notebook (*.ipynb). Click the "Run in Colab" link on the top of the lab. That's it!

There were 3 labs in the course and the solution python notebooks can be found in :

  1. Lab1 covering the introduction and RNNs
  2. Lab2 covering CNNs and Deep Generative Modelling
  3. Lab3 covering RL Basics

As I complete these labs, I will be adding some comments, mainly for myself, on how I would increase the scope of the lab and go beyond an exerise, to a fully fledged project

Running the labs

Now, to run the labs, open the Jupyter notebook on Colab. Navigate to the "Runtime" tab --> "Change runtime type". In the pop-up window, under "Runtime type" select "Python 3", and under "Hardware accelerator" select "GPU". Go through the notebooks and fill in the #TODO cells to get the code to compile for yourself!

License

All code in this repository is copyright 2020 MIT 6.S191 Introduction to Deep Learning. All Rights Reserved.

Licensed under the MIT License.

© MIT 6.S191: Introduction to Deep Learning

http://introtodeeplearning.com

Written with StackEdit.