Deep Learning
from Scratch

Introduction to Deep Learning and Neural Networks Basics

Course starts soon..


QUIZ


We will start now with a quiz based on the first week material

You have 7 minutes to answer the quiz.

The quiz link:
Quiz Link
It will be copied in Mattermost and in the Zoom chat.

Matrices in python

A Notebook to play with matrices

RESOURCES


In case you need more material, you can check out these websites:

  • Academic: Papers With Code
  • Short Videos: Two Minute Papers
  • Video Lectures: Stanford CS230: Deep Learning
  • Articles: Medium
  • Book: Deep Learning Book
  • Q&A: StackExchange

Please add on our Mattermost Chat if have more ideas!

Papers with Code

Two Minute Papers Videos

Stanford Deep Learning Course

Medium Articles

The Deep Learning Book

It is availabe in HTML format on the website.
A PDF version was created on Github

Community Exchange

The largest community for Q&A.

Paper of the Week

Deep Learning, Y. LeCunn, Y. Bengio and G. Hinton,
Nature, 2015

QUIZ (15 mins)


1. Why is deep learning interesting for many application?
2. What is structured or unstructured data? When using supervised learning, which one should we use?
3. Why is the cost function important and why we need such a function for logistic regression?
3b. Are you familiar with the concept of convex functions and why this helps gradient find the minimum?
4. Is the concept of gradient descent clear? How do learning rate correlates to number of iterations?
5. Why is vectorization faster than a loop in python?
5b. Is it always the case? Can you think of a case when vectorization is not faster, or even slower?

DISCUSSION AND ANSWERS


Cost Function

Image from this article.

Non Convex Functions

Gradient Descent

Image from this article.

Vectorization

A nice explanation about what vectorization is
and
An interesting discussion on Stackoverflow

Exercise (15-20 mins)

We go through the programming assignment that were planned for this week.

Open Source Project of the Week

Fashion MNIST Datasets

Github Repository with Examples for MNIST Datasets

Why?

Conclusions

It is a good playground for your first project
A reward to motivate you further

For the next week