Last modified on 27 Jul 2020.

This is my note for the course (Convolutional Neural Networks). The codes in this note are rewritten to be more clear and concise.

🎯 Overview of all 5 courses.

πŸ‘‰ Course 1 – Neural Networks and Deep Learning.
πŸ‘‰ Course 2 – Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization.
πŸ‘‰ Course 3 – Structuring Machine Learning Projects.
πŸ‘‰ Course 5 – Sequence Models.

This course will teach you how to build convolutional neural networks and apply it to image data.

Computer vision

  • Challenges of computer vision: inputs get really big. β‡’\Rightarrow Easily lead to overfitting and infeasible!

Edge Detection

  • We wanna detect vertical / horizontal edges. βˆ—* is called a convolution operator. The 3Γ—33\times 3 square is called a filter (kernel)

    Horizontal edge detection Horizontal edge detection.ref

    Vertical vs horizontal Vertical vs Horizontal.ref

  • There are many different filers we could use. Sobel filter and Scharr filter β€˜s advantage is that it allows you to put a little bit more weight to the central row of the central pixel, this makes it maybe a little bit more robust.

    Sobel filter and Scharr filter Sobel filter and Scharr filter.ref

References

πŸ‘‰ Course 5 – Sequence Models.

β€’Notes with this notation aren't good enough. They are being updated. If you can see this, you are so smart. ;)