Deep Learning Study Notes

A collection of my Deep Learning LaTeX study notes of the CS231n course, the Deep Learning book and some other random sources.

All credits go to L. Fei-Fei, A. Karpathy, J.Johnson teachers of the CS231n course. Thank you for this amazing course!!

Structure

Two options to chose from:

• FULL DOCUMENT
• Individual chapters

If you chose individidual chapters here is the list (are you sure you do not prefer the FULL DOCUMENT?):

1. Data

2. Data Preprocessing

3. Data Augmentation and Transfer Learning

4. Learning

5. Neural Network

6. Parameters Initialization

7. Activation Function

8. Loss function

9. Backpropagation

10. Parameters Update

11. Dropout

12. Hyper-Parameters selection and babysitting

13. Other definitions

14. Tricks

15. Visualization

16. Layers

17. Input Layer

18. Convolutional layer

19. Pooling layer

20. Batch Normalization layer

21. Upsampling Layer (“Transposed Convolution”)

22. Fully Connected Layer

23. Highway Layer

24. Networks

25. Recurrent Neural Networks (RNN)

26. Autoencoders

27. Generative Adversarial Nets

28. Region Based CNN (R-CNN)

29. YOLO

30. RNN ConvNet

31. Attention Models

32. Spatial Transformer Networks

33. Famous Networks

34. Applications

35. Bibliography

Contributions

More than happy to accept contributions

Some Keywords

deep learning notes, CS231n notes, convolutional neural networks, ConvNets, CNN, RNN, LSTM, recurrent neural networks, R-CNN, YOLO, GAN

Acknowledgements & Credits

All credits go to L. Fei-Fei, A. Karpathy, J.Johnson teachers of the CS231n course. Thank you for this amazing course!!