Learning-Resources

Collection of all learning material

1. Norms: https://medium.com/@montjoile/l0-norm-l1-norm-l2-norm-l-infinity-norm-7a7d18a4f40c

2. Max. Likelihood Function: https://medium.com/quick-code/maximum-likelihood-estimation-for-regression-65f9c99f815d

3. Posterior and Prior: https://medium.com/@SeoJaeDuk/archived-post-random-notes-for-prior-and-posterior-1116d34695f7

4. MLE and MAP with example: https://towardsdatascience.com/a-gentle-introduction-to-maximum-likelihood-estimation-and-maximum-a-posteriori-estimation-d7c318f9d22d

5. Kernels: https://towardsdatascience.com/kernel-function-6f1d2be6091

6. Forward Propagation: https://towardsdatascience.com/forward-propagation-in-neural-networks-simplified-math-and-code-version-bbcfef6f9250

7. Softmax, Negative Likelihood, Derivative of Softmax: https://ljvmiranda921.github.io/notebook/2017/08/13/softmax-and-the-negative-log-likelihood/

8. Coding a basic 2 layer NN: https://towardsdatascience.com/coding-a-2-layer-neural-network-from-scratch-in-python-4dd022d19fd2

9. Generative Adversarial Networks (GANs): https://medium.com/free-code-camp/an-intuitive-introduction-to-generative-adversarial-networks-gans-7a2264a81394

10. Principal Component Analysis(PCA): https://medium.com/codex/principal-component-analysis-pca-how-it-works-mathematically-d5de4c7138e6

11. Singular Value Decomposition: https://towardsdatascience.com/svd-8c2f72e264f

12. Convolutional Neural Networks (CNNs) - CS231 - Stanford https://www.youtube.com/playlist?list=PLC1qU-LWwrF64f4QKQT-Vg5Wr4qEE1Zxk

13. Gaussian mixture models https://towardsdatascience.com/gaussian-mixture-models-d13a5e915c8e

14. Variational Autoencoder

• reparameterization trick: https://gokererdogan.github.io/2016/07/01/reparameterization-trick/?source=post_page-----77fd3a8dd368----------------------
• VAE tutorial: https://jaan.io/what-is-variational-autoencoder-vae-tutorial/?source=post_page-----77fd3a8dd368---------------------- and https://towardsdatascience.com/generating-images-with-autoencoders-77fd3a8dd368

14. Transformers (NLP) - https://medium.com/analytics-vidhya/how-do-transformers-work-in-nlp-a-guide-to-the-latest-state-of-the-art-models-52424082c132

15. RNN/LSTM - http://colah.github.io/posts/2015-08-Understanding-LSTMs/

16. Attention in NLP - https://medium.com/@joealato/attention-in-nlp-734c6fa9d983

17. Support Vector Machines(SVM) - https://classroom.udacity.com/courses/ud262/lessons/386608826/concepts/3758388600923 (ML GeorgiaTech Udacity course -> Kernels & SVM)

18. YouTube channels - Statistics, Data Science general concepts

    • https://www.youtube.com/c/BrandonFoltz
    • https://www.youtube.com/user/SpartacanUsuals

19. MLOps - https://madewithml.com/#foundations

20. ML interviews - https://huyenchip.com/ml-interviews-book/