diff --git a/content/portfolio/What is Machine Learning.md b/content/portfolio/What is Machine Learning.md index d20b3c7..bb9f073 100644 --- a/content/portfolio/What is Machine Learning.md +++ b/content/portfolio/What is Machine Learning.md @@ -26,31 +26,55 @@ In this article, we will cover: To start, it is important to understand the three main categories of machine learning: -1. **Supervised Learning** This type of learning relies on labeled data, where the model learns to map inputs XXX to outputs yyy. Common tasks include:\* **Classification**: Assigning data to categories (e.g., spam detection).\* **Regression**: Predicting continuous values (e.g., house price estimation).![ML Model Types.png](/portfolio/What%20is%20Machine%20Learning/ML%20Model%20Types.png) -2. **Unsupervised Learning** In this case, no labels are provided, and the goal is to find structures or patterns. Common tasks include:\* **Clustering**: Grouping similar data points (e.g., customer segmentation).\* **Dimensionality Reduction**: Simplifying data while retaining key information (e.g., PCA).* **Anomaly Detection**: Identifying unusual data points (e.g., fraud detection). +1. **Supervised Learning** This type of learning relies on labeled data, where the model learns to map inputs $X$ to outputs $y$. Common tasks include: + +- **Classification**: Assigning data to categories (e.g., spam detection). +- **Regression**: Predicting continuous values (e.g., house price estimation). + +2. **Unsupervised Learning** In this case, no labels are provided, and the goal is to find structures or patterns. Common tasks include: + +- **Clustering**: Grouping similar data points (e.g., customer segmentation). +- **Dimensionality Reduction**: Simplifying data while retaining key information (e.g., PCA). +- **Anomaly Detection**: Identifying unusual data points (e.g., fraud detection). + 3. **Reinforcement Learning** This learning type involves an agent interacting with an environment. The agent learns by trial and error to maximize cumulative rewards, as seen in robotics and gaming. +![ML Model Types.png](/portfolio/ML/types.png) + With this overview of ML types, let’s now focus on supervised learning, the most widely used approach, and explore how to choose the right model. ## Three Considerations for Choosing a Supervised Learning Model Selecting the right supervised learning model is critical and depends on several factors: -1. **Problem Type**\* Is it a regression or classification problem?\* **Key Point**: Determine if the target variable is continuous or discrete. -2. **Problem Complexity**\* Is the relationship between input features and the target variable linear or nonlinear?\* **Key Point**: Understand whether the data allows for easy predictions or requires more complex models. -3. **Algorithmic Approach**\* Should you choose a feature-based or similarity-based model?\* **Key Point**: The choice of the model (e.g., linear regressions vs k-NN) depends on the dataset’s size and complexity. +1. **Problem Type** + +- Is it a regression or classification problem? +- **Key Point**: Determine if the target variable is continuous or discrete. + +2. **Problem Complexity** + +- Is the relationship between input features and the target variable linear or nonlinear? +- **Key Point**: Understand whether the data allows for easy predictions or requires more complex models. + +3. **Algorithmic Approach** + +- Should you choose a feature-based or similarity-based model? +- **Key Point**: The choice of the model (e.g., linear regressions vs k-NN) depends on the dataset’s size and complexity. Once the model type is defined, the next step is to delve into the full workflow of developing an ML model. -# The Typical Workflow in Machine Learning +## The Typical Workflow in Machine Learning A machine learning project generally follows these steps: -1. **Data Preparation**\* Splitting data into training and testing sets.\* Preprocessing: scaling, handling missing values, etc. -2. **Model Training**\* Fitting the model on training data: `model.fit(X, y)`.\* Optimising parameters and hyperparameters. -3. **Prediction and Evaluation**\* Making predictions on unseen data: `model.predict(X)`.\* Comparing predictions ($\hat{y}$​) with actual values ($y$).![Modelization in Prog.png](/portfolio/What%20is%20Machine%20Learning/Modelization%20in%20Prog.png) +1. **Data Preparation** Splitting data into training and testing sets.\* Preprocessing: scaling, handling missing values, etc. +2. **Model Training** Fitting the model on training data: `model.fit(X, y)`.\* Optimising parameters and hyperparameters. +3. **Prediction and Evaluation** Making predictions on unseen data: `model.predict(X)`.\* Comparing predictions ($\hat{y}$​) with actual values ($y$). -**Transition:** Evaluation is a crucial step to verify the performance of a model. For regression problems, the R² score is a key indicator. +![Modelization in Prog.png](/portfolio/ML/model.png) + +Evaluation is a crucial step to verify the performance of a model. For regression problems, the R² score is a key indicator. ## Evaluating Models: The R² Score @@ -65,7 +89,7 @@ Where: A $R^2$ close to 1 indicates a good fit. -![R2 Score.png](/portfolio/What%20is%20Machine%20Learning/R2%20Score.png) +![R2 Score.png](/portfolio/ML/R2.png) With these concepts in mind, you are better equipped to understand and apply ML models in your projects. diff --git a/content/portfolio/how-my-website-works.md b/content/portfolio/how-my-website-works.md index d23515a..95f8373 100644 --- a/content/portfolio/how-my-website-works.md +++ b/content/portfolio/how-my-website-works.md @@ -13,7 +13,7 @@ My personal website is an overengineered playground where I tinker, explore new While it's still fresh in my mind, I wanted to document how this version of the site works, the tools I used to build it, and the challenges I overcame to bring it to its current state. -![Website](/portfolio/how-my-website-works/website.png) +![Website](/portfolio/website-work/website.png) ## Ideas and Goals @@ -63,7 +63,7 @@ Nuxt UI aims to provide everything you need for the UI when building a Nuxt app, #### NuxtHub & Cloudflare workers -![NuxtHub](/portfolio/how-my-website-works/nuxt-hub.png) +![NuxtHub](/portfolio/website-work/nuxt-hub.png) NuxtHub is an innovative deployment and management platform tailored for Nuxt, leveraging the power of Cloudflare. Deploy your application effortlessly with database, key-value, and blob storage—all configured seamlessly within your Cloudflare account. @@ -81,7 +81,7 @@ One word : `If you know SQL — you know Drizzle.` #### Nuxt Studio -![Nuxt Studio](/portfolio/how-my-website-works/nuxt-studio.png) +![Nuxt Studio](/portfolio/website-work/nuxt-studio.png) Nuxt Studio introduces a fresh editing experience for your Nuxt Content website, providing limitless customization and a user-friendly interface. Edit your website effortlessly with our editor reminiscent of Notion, fostering seamless collaboration between developers and copywriters. It offers a rich text editor, markdown support, and a live preview, enabling you to create and edit content with ease. diff --git a/public/portfolio/What is Machine Learning/Modelization in Prog.png b/public/portfolio/ML/model.png similarity index 100% rename from public/portfolio/What is Machine Learning/Modelization in Prog.png rename to public/portfolio/ML/model.png diff --git a/public/portfolio/What is Machine Learning/R2 Score.png b/public/portfolio/ML/r2.png similarity index 100% rename from public/portfolio/What is Machine Learning/R2 Score.png rename to public/portfolio/ML/r2.png diff --git a/public/portfolio/What is Machine Learning/ML Model Types.png b/public/portfolio/ML/types.png similarity index 100% rename from public/portfolio/What is Machine Learning/ML Model Types.png rename to public/portfolio/ML/types.png diff --git a/public/portfolio/how-my-website-works/nuxt-hub.png b/public/portfolio/website-work/nuxt-hub.png similarity index 100% rename from public/portfolio/how-my-website-works/nuxt-hub.png rename to public/portfolio/website-work/nuxt-hub.png diff --git a/public/portfolio/how-my-website-works/nuxt-studio.png b/public/portfolio/website-work/nuxt-studio.png similarity index 100% rename from public/portfolio/how-my-website-works/nuxt-studio.png rename to public/portfolio/website-work/nuxt-studio.png diff --git a/public/portfolio/how-my-website-works/website.png b/public/portfolio/website-work/website.png similarity index 100% rename from public/portfolio/how-my-website-works/website.png rename to public/portfolio/website-work/website.png