<aside> 💡 Jupyter Notebook are great for ML experiments. Jeremy Howard uses one Notebook for each model he builds. He simply duplicates the Notebook, as he explained here. According to him, its the fastest and most simple way to work. Tip: you can work with both notebooks and scripts, as seen in this github folder where we import all scripts into the notebook.

</aside>

<aside> 💡 There are thousands of machine learning algorithms, but you'll rarely need more than a handful.

A good start (link):

• Linear Regression / Logistic Regression
• Decision Trees
• Deep Neural Networks
• XGBoost
• K-Nearest Neighbors (KNN)
• K-means clustering
• PCA or better: UMAP </aside>

“You have to understand how an algorithm works internally if you want to use it" is bullshit advice. I often use/apply algorithms without knowing how they work internally and that's fine. In fact, using an algorithm can help build intuition for how it works, which will make it easier to then learn how it really works.

• Overview about all algorithms: Algorithms in a nutshell
• Gute visuelle Übersicht über die wichtigsten Algorithmen → video
• All Machine Learning Models Explained in 5 Minutes | Types of ML Models Basics

• Inputs: These are the data points fed into the system (like images, text, or numbers).
• Parameters: These are the adjustable values that the model learns during training.
• Architecture: This is the structure or design of the model that processes the inputs using the parameters.
• Predictions: These are the outputs that the model generates based on the inputs.
• Labels: These are the correct answers or ground truth that the model is trying to match.
• Loss: This measures how far off the model's predictions are from the correct labels.
• Update: This is the key feedback loop where the model's parameters are adjusted based on the loss to improve future predictions.
• → Backpropagation

Limitations