Convolutional Neural Networks
Deep Learning
Main Idea
The concept is inspired by the anatomy of the visual cortex and the image representations in the brain.
Seminal Paper:
What was found:
How can computers represent images?
How can we simulate the electrical activity in the brain?
Answer: we can use numbers and special functions called “convolutions.”
Convolutions are based on image filters
How convolutions work:
Padding needs to be considered:
Intuitive example:
What happens in an activation layer:
Example for the neural network architecture:
Pooling:
Dropout:
The anatomy of a convolutional neural network:
Some intuition:
More intuition:
Example Applications: