Taking the Coursera Deep Learning Specialization, Neural Networks and Deep Learning course. Will post condensed notes every week as part of the review process. All material originates from the free Coursera course, taught by Andrew Ng. See deeplearning.ai for more details.
Table of Contents
Introduction to Deep Learning
There are five courses in the Coursera Deep Learning Specialization. (This is course 1.)
- Neural Networks and Deep Learning
- Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization
- Structuring your Machine Learning Project
- Convolutional Neural Networks
- Natural Language Processing: Building Sequence Models.
What is a Neural Network
A neural network is a learning algorithm comprised of many stacked neurons. THey are chained together to create representations of functions based on input data.
Supervised Learning with Neural Networks
Supervised learning is when you are given specific inputs and outputs. For instance, in the housing pricing example you can have
x: number of bedrooms, size of house, ..., house features map to
y: price of house. These types of algorithms can calculate a given
y with input
x. Typically the machine is trained on data that has both
Why is Deep Learning Taking Off?
Primarily 3 reasons:
- Massive increase in collected data
- Increase in computational power
- Algorithm modifications (usually increases computation speed)
About this Course
This course is broken out into four weeks.
- Week 1: Introduction
- Week 2: Basics of Neural Network Programming
- Week 3: One Hidden Layer Neural Networks
- Week 4: Deep Neural Networks
Optional: Heroes of Deep Learning (Geoffrey Hinton)
Interview between Andrew Ng and Geoffrey Hinton.
Move on to Week 2.