CS231N Study Note
Study Notes taken from Standford CS231N course from youtube.
- Abstrast
- Lecture 1 | Introduction to Convolutional Neural Networks for Visual Recognition
- Lecture 2 | Image Classification Pipelines
- Lecture 3 | Loss Function and Optimization
- Lecture 4 | Backpropagation and Neural Network
- Lecture 5 | Convolutional Neural Network
- Lecture 6 | Training Neural Network 1
- Lecture 7 | Training Neural Network 2
Abstrast
This course conducted by Standford focus on Computer Vision and Deep Learning, and is focus from the basic to the somehow advanced topic. This notebook contain the archives of the note of me taking from the course. If you would like to contribute to the notebook, please leave a comment in the below of the notebook.
Link to youtube lecture
Lecture 1 | Introduction to Convolutional Neural Networks for Visual Recognition
Brief introduction to the history of Computer Vision, Deep Learning and the problems to tackle in Computer Vision.
Link to my Note
Lecture 2 | Image Classification Pipelines
Introduction to the image classification pipelines and train a simple model for image classification.
Link to my Note
Lecture 3 | Loss Function and Optimization
Introduction to hinge loss, softmax function and optimization.
Link to my Note
Lecture 4 | Backpropagation and Neural Network
Introduction to Neural Network backpropagation flow, equations and intuiation.
Link to my Note
Lecture 5 | Convolutional Neural Network
History and modern about CNN and its basic operations.
Link to my Note
Lecture 6 | Training Neural Network 1
Basic Training Procedure hyperparameters optimization.
Link to my Note
Lecture 7 | Training Neural Network 2
Basic Training Procedure hyperparameters optimization.
Link to my Note