Deep Into CNN

Contains material relevant to "Deep Into CNN" Project.

Resources

Week 1 : Regression( Skip if you are confident )

Readings

1. Local Setup (Use Conda : recommended)
   https://jupyter.readthedocs.io/en/latest/install/notebook-classic.html https://docs.conda.io/projects/conda/en/latest/user-guide/install/index.html#installation
2. (Optional: Basic Python and libraries) https://duchesnay.github.io/pystatsml/index.html#scientific-python
3. ( Optional : For those with very basic ml knowledge: Only 2.1-2.7) https://www.youtube.com/watch?v=PPLop4L2eGk&list=PLLssT5z_DsK-h9vYZkQkYNWcItqhlRJLN
4. Linear Regression:
   https://medium.com/analytics-vidhya/simple-linear-regression-with-example-using-numpy-e7b984f0d15e
5. Logistic Regression: https://towardsdatascience.com/logistic-regression-detailed-overview-46c4da4303bc

Practice Material

Find in NeuralNetIntro : W2-3.

Week 1-2: Neural Networks

Readings

1. This one is highly recommended:
   https://www.youtube.com/playlist?list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi
   Some more material (bit extensive, so be careful):
   https://youtube.com/playlist?list=PLtBw6njQRU-rwp5__7C0oIVt26ZgjG9NI
2. Basic Backprop:
   https://ml-cheatsheet.readthedocs.io/en/latest/backpropagation.html
3. Backprop (Mathematical Version):
   https://mattmazur.com/2015/03/17/a-step-by-step-backpropagation-example/
4. Softmax:
   https://ljvmiranda921.github.io/notebook/2017/08/13/softmax-and-the-negative-log-likelihood/
5. Pytorch(Skip the CNN part if you want for now):
   https://pytorch.org/tutorials/beginner/basics/intro.html
6. Optional guide:
   http://neuralnetworksanddeeplearning.com/chap1.html

Practice Material

Find in PyTorch : W2-3.