A beginner's guide to the fundamentals of deep learning

NaN.

This course consists of:

14 Tutorials

Tutorials have been chosen to maximize learning curve, i.e. learn the most in the shortest amount of time. Tutorials cover introductory topics for deep learning!

Expected time to completion: 2-3 weeks (10-15 sessions)

Pre-requisites: Calculus (specifically, differentiation)

Pro-tip: If you want to skip sections or tutorials, mark them as completed.

Syllabus

Machine Learning basics: what it is, gradient descend

A Visual Introduction (and Review) of Machine Learning
2 mins
What is Machine Learning? Why Machine Learning?
11 mins
Perceptron algorithm
4 mins
Tutorial: Linearly separable data
2 mins
Quiz: Perceptron algorithm
6 mins

Deep Learning basics: what it is, neural networks, computational graphs, back-propagation

Deep Learning in a Nutshell
32 mins
A Neural Network Playground
1 min
Gradient Descent intuition
2 mins
Calculus on Computational Graphs: Backpropagation -- colah's blog
2 mins
Andrej Karpathy: Yes you should understand backprop
2 mins

Convolutional Neural Networks: the most successful architecture for computer vision

Recurrent Neural Networks: the most successful architecture for natural language processing, and other domains with sequential input

A Deep Dive into Recurrent Neural Nets
21 mins
Understanding LSTM Networks -- colah's blog
2 mins

Start this course

A Visual Introduction (and Review) of Machine Learning

Category: Deep Learning

Comment