This is a series of articles on machine learning that I wrote while following Andrew Ng’s course on Machine Learning course on Coursera, and his Deep Learning specialization. The articles gradually grew in scope while I explored other resources, among which but not limited to:

The single sections are built using Jupyter notebooks and converting them in markdown. Almost all figures and computations are coded in Python and, while they are hidden in the typographic version of the article, they are freely accessible from notebook source code.

See the source code here: github repository

While the scope and plots grew in complexity I ended up needing more powerful tools than those available at the time. This prompted me to write and publish some python libraries to help me out:

    1. What is Machine Learning

    2. Preparatory concepts

    3. Linear Regression - Model Representation

    4. Linear Regression - Cost Function

    5. Linear Regression - Gradient Descent

    6. Linear Regression - Implementation

    7. Logistic Regression - Model Representation

    8. Logistic Regression - Cost function

    9. Logistic Regression - Multiclass Classification

    10. Logistic Regression - Implementation

    11. Overfitting and Regularization

    12. Neural Networks - Motivation

    13. Neural Networks - Model Representation

    14. Neural Networks - Applications

    15. Neural Networks - Cost Function

    16. Neural Networks - Backpropagation

    17. Neural Networks - Backpropagation 2

    18. Machine learning diagnostic

    19. System design - numerical evaluation

    20. System design - Error for skewed classes

    21. Neural network - Implementations

    22. SVM - Large Margin Classification

    23. SVM - Kernels

    24. Unsupervised Learning - K-Means

    25. Unsupervised Learning - Dimensionality Reduction

    26. Anomaly Detection

    27. Recommendation systems

    28. Deep Learning

    29. Deep Learning - Bias & Variance

    30. Deep Learning - $L_2$ reguralization

    31. Deep Learning - Dropout regularization

    32. Deep Learning - Optimization - Normalization

    33. Deep Learning - Optimization - Mini batch

    34. Deep Learning - Optimization - Rolling techniques

    35. Deep Learning - Optimization - Tuning

    36. Deep Learning - Softmax classifier

    37. Deep Learning - CNN - Convolution

    38. Deep Learning - CNN - Convolutional NN

    39. Deep Learning - CNN - Case Studies

    40. Deep Learning - CNN - Using pre-designed networks

    41. Deep Learning - CNN - Object detection

    42. Deep Learning - CNN - YOLO

    43. Deep Learning - CNN - U-Net

    44. Deep Learning - CNN - Face verification

    45. Deep Learning - CNN - Neural style transfer

    46. Deep Learning - CNN - 1D/3D generalization

    47. Deep Learning - RNN - Sequence models

    48. Deep Learning - RNN - RNN architectures

    49. Deep Learning - RNN - Word embeddings

    50. Deep Learning - RNN - Sequence to sequence models

    51. Deep Learning - RNN - Attention Model

    52. RNN - Implementations

    53. Deep Learning - RNN - Transformer network