A collection of interactive web tools for exploring machine learning algorithms step by step. Each tool breaks down a core ML concept into transparent, visual calculations — no black boxes.
🔗 Live: abka0002.github.io/Machine-Learning-Explained
| Tool | Description |
|---|---|
| Data Preparation & Feature Engineering | Interactive pipeline covering EDA, data types, imputation, scaling, encoding, and feature selection with the Heart Failure dataset |
| Linear Regression | Simple and multiple Linear regression Deployment |
| Bias and Variance tradeoff | Bias–Variance & Generalization Explorer |
| Grid search and K-Fold Cross Validation | Discover how GridSearchCV from Scikit-Learn calculates the mean and standard deviation of validation folds to find the best α for a Lasso regression Model, and how refit=True fully leverages your training data. |
| Sklearn Pipeline | Explaining How can sklearn pipeline Chaining preprocessing steps and a model into a single, reproducible workflow. |
| SMOTE & SMOTE-NC | Step-by-step walkthrough of synthetic oversampling for imbalanced datasets, covering both continuous and mixed-type features |
| Attention Is All You Need | Interactive guide to the Transformer architecture — self-attention, multi-head attention, positional encoding, encoder-decoder, and masking |
These tools are designed for students and practitioners who want to go beyond using ML libraries as black boxes. Each app lets you follow the actual math behind an algorithm — see how distances are computed, how neighbors are selected, and how new samples are generated.
All tools run entirely in the browser. No server, no installation, no sign-up required.
Pure HTML, CSS, and JavaScript — no build step, no frameworks, no dependencies.
Contributions are welcome. To add a new tool, create a folder with an index.html inside it and open a pull request.
MIT