This GitHub repository will be regularly updated with the lecture materials covered each week. It will also include additional resources for practice, along with projects and other learning materials to support your progress.
The content of this repository is bassed off the materials covered by Yusuf last year (https://github.com/YM2132) and I will be using some of his contents to complement the lectures (https://github.com/YM2132/QMML). The structure of the course also follows a very simmilar style of the Machine Learning Specialization from Andrew Ng (https://www.coursera.org/specializations/machine-learning-introduction)
Lectures:
- Lecture 1: Gradient Descent Algorithm
- Lecture 2: Simple Liner Regression
- Lecture 3: Multiple Linear Regression
- Lecture 4: Neural Networks - Forwards Pass and ReLU
- Lecture 5: Neural Networks - Backpropagation from scratch + Pytorch and TensorFlow implementation
- Lecture 6: Neural Networks to multiclass classification task in PyTorch
Extra Learning Resources:
- Mathematics for ML: https://mml-book.github.io/
- Neural Networks (Videos from easier to harder difficulty)
- https://www.youtube.com/watch?v=cAkMcPfY_Ns
- https://www.youtube.com/watch?v=aircAruvnKk&list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi
- https://www.youtube.com/watch?v=IHZwWFHWa-w&list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi&index=2
- https://www.youtube.com/watch?v=Ilg3gGewQ5U&list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi&index=3
- https://www.youtube.com/watch?v=tIeHLnjs5U8&list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi&index=4
- The Adam Optimizer: https://www.youtube.com/watch?v=MD2fYip6QsQ)](https://www.youtube.com/watch?v=MD2fYip6QsQ
- MultiClassification Explained by Andrew Ng: https://www.youtube.com/watch?v=ZvaELFv5IpM
- Full free course on Pytroch for ML: https://www.youtube.com/watch?v=V_xro1bcAuA&t=2598s