Skip to content

Latest commit

 

History

History
34 lines (25 loc) · 9.79 KB

README.md

File metadata and controls

34 lines (25 loc) · 9.79 KB

machine-learning-nutsnbolts

The nuts and bolts of machine learning and insights into its operations. Generated by DALL·E 3.

DALL·E 2024-02-08 18 09 28 - Create a wide-format, detailed illustration that visualizes The nuts and bolts of machine learning without including any characters or letters This

This repository aims to organize implementations of machine learning algorithms and demonstrate practical ways to apply or use machine learning models. I initiated this project to refresh and reinforce my fading knowledge of previously learned concepts, deepen my understanding of various algorithms, and examine examples of their practical applications.

Algorithms

Here is an overview of machine learning algorithms that are either currently implemented or planned for future implementation. Additionally, this table presents supplementary materials I have prepared to revisit and strengthen my understanding of what I learned.

Notes: The "Colab" links will take you to the Google Colab notebook, where you can view the implementation and run the code. The "DEV" column contains links to articles I have written.

Category Algorithms Colab DEV
Optimization Exploring Gradient Descent Variants: Batch, Mini-Batch, Stochastic, and Fundamentals of Implementation Gradient descent Dev.to blog
Optimization Comparing Optimizers: Gradient Descent, Momentum, AdaGrad, and Adam Implemented from Scratch Optimization algorithms
Preprocessing Implementing Feature Scaling Methods: Standardization (Z-score normalization) and Normalization (Min-Max scaling) Feature scaling (Standardization / Normalization) Dev.to blog
Supervised Implementing Linear Regression from Scratch: Gradient Descent, Mean Squared Error (MSE) Loss, and L1/L2 Regularization Explained Linear regression / Regularization Dev.to blog
Supervised Implementing Logistic Regression for Classification from Scratch: Cross-entropy loss, One-hot encoding, and Activation function (Sigmoid/Softmax) Explained Logistic regression for classification / Activation function (Sigmoid / Softmax) / One-hot encoding Dev.to blog
Supervised Implementing Neural Network for Classification with ReLU and Backpropagation from Scratch to PyTorch Neural Network for classification
Supervised Implementing K-Nearest Neighbor (k-NN) for Classification from Scratch k-NN for classification Dev.to blog
Unsupervised Implementing K-means for Clustering from Scratch k-means for clustering
Unsupervised Implementing Principal Component Analysis (PCA) for Dimensionality Reduction from Scratch PCA for dimensionality reduction
Reinforcement Implementing Multi-Armed Bandit (MAB) from Scratch Multi-Armed Bandit (MAB) and Reinforcement learning

The above implementations are based on the following resources: