Data Science:Deep Learning In Python

Course Features

Course Details

Section 1 What is a neural network?
Introduction and Outline
Neural Networks with No Math
An almost purely qualitative description of neural networks.
Where does this course fit into your deep learning studies?
Section 2: Classifying more than 2 things at a time
Softmax
What\'s the function we use to classify more than 2 things?
Softmax in Code
How do we code the softmax in Python?
Building an entire feedforward neural network in Python
Let\'s extend softmax and code the entire calculation from input to output.
Section 3: Training a neural network
Backpropagation Intro\r\n
Backpropagation - what does the weight update depend on?
A further look into backpropagation.
Backpropagation – recursiveness
Backpropagation for deeper networks, exposing the structure, and how to code it more efficiently.
Backpropagation in code
How to code bacpropagation in Python using numpy operations vs. slow for loops.
Section 4: Practical concerns k
Donut and XOR Review
Donut and XOR Revisited
We look again at the XOR and donut problem from logistic regression. The features are now learned automatically.
Hyperparameters
Section 5: TensorFlow and the Future k
A look at Google\'s new TensorFlow library.
Where to go from here
What did you learn? What didn\'t you learn? Where can you learn more?
This course does not have any sections.

More Courses by this Instructor