🇫🇷
Search posts...

Concepts

Discover the key concepts that form the backbone of machine learning and AI. Each post breaks down complex ideas into clear, practical insights.

1 post

Workflow

ML

  1. 01 Overview of the End-to-End Machine Learning Engineering Workflow
    Overview of the End-to-End Machine Learning Engineering Workflow

    Learn the four pipelines with a practical tour of the end-to-end ML workflow (from data to models to deployment).

1 post

Data Pipeline

Cleaning / Wrangling

  1. 01 Data Cleaning & Wrangling – From Raw Mess to ML-Ready Data
    Data Cleaning & Wrangling – From Raw Mess to ML-Ready Data

    Explore the essential techniques to clean, transform, and structure raw data before feeding it into machine learning models.

5 posts

ML Pipeline

Algorithms

  1. 01 LSTMs - The RNNs That Actually Remember Things 🤖🧠
    LSTMs - The RNNs That Actually Remember Things 🤖🧠

    Remember how RNNs tend to forget things too quickly? That’s where LSTMs come in! LSTMs are fancy RNNs built to handle sequential data without forgetting important details every few steps.

  2. 02 RNN - Step-by-Step Visual Guide
    RNN - Step-by-Step Visual Guide

    Ever wondered how your phone predicts the next word while you're texting? That's the magic of **Recurrent Neural Networks (RNNs)** at work! RNNs are like those friends who remember everything you say and use it against you... I mean, use it to make better predictions. 🤖💡

Model Engineering

  1. 01 Tokenization - Comprehensive Guide
    Tokenization - Comprehensive Guide

    Tokenization is a foundational step in Natural Language Processing (NLP). Whether you’re building a sentiment analysis model, a text classifier, or a large language model (LLM) like GPT, understanding tokenization is essential.

  2. 02 Embeddings - Comprehensive Guide
    Embeddings - Comprehensive Guide

    Embeddings are the mathematical foundation that enables machines to understand and work with language. After tokenization converts text to numbers, embeddings transform those numbers into meaningful representations that capture semantic relationships.

Optimization

  1. 01 DAPO - 4 Optimization Techniques to Enhance AI Mathematical Reasoning
    DAPO - 4 Optimization Techniques to Enhance AI Mathematical Reasoning

    Ever wondered how ChatGPT solves complex problems? Some researchers just released DAPO, an open-source method that’s outperforming the secret sauce from companies like OpenAI and DeepSeek. Let’s break it down

3 posts

Projects

OCR

  1. 01 Building an Advanced OCR Application with Llama 4 Scout Models
    Building an Advanced OCR Application with Llama 4 Scout Models

    Ever tried to copy text from a handwritten note or a screenshot? That's why I decided to build something cool using Meta's new Llama 3.2 vision models

  2. 02 Extracting LaTeX from Images using GPT-4o and Streamlit
    Extracting LaTeX from Images using GPT-4o and Streamlit

    Encountered a mathematical equation in an image and wished you could extract its LaTeX code instantly? I built a LaTeX OCR tool using GPT-4o and Streamlit.

N8N

  1. 02 N8N + RAG + PineCone + OpenAI - Turning 500 Legal Documents into an AI Assistant
    N8N + RAG + PineCone + OpenAI - Turning 500 Legal Documents into an AI Assistant

    What if your 500 legal PDFs could answer questions like a trained paralegal — instantly and with sources cited?

3 posts

Agents

AI Agents

  1. 01 Understanding AI Agents: Types, Behaviors, and Frameworks Explained
    Understanding AI Agents: Types, Behaviors, and Frameworks Explained

    AI agents are intelligent systems designed to autonomously perform tasks, make decisions, or provide insights based on their programmed goals. These agents can operate independently or collaboratively, depending on their design, and are widely used in domains ranging from customer support to autonomous vehicles.

  2. 02 Agentic AI vs. Agents AI : the Future of Autonomous Systems
    Agentic AI vs. Agents AI : the Future of Autonomous Systems

    A clear breakdown of the differences and overlaps between agentic AI and software agents, highlighting their behaviors, architectures, and implications for developers building autonomous systems.

RAG

  1. 01 RAG Developer’s Toolkit - The Must-Have Tools for LLMs & Retrieval
    RAG Developer’s Toolkit - The Must-Have Tools for LLMs & Retrieval

    I’ve compiled this RAG Developer’s Toolkit to help navigate the growing AI ecosystem. Whether you’re working on vector databases, multi-agent systems, or document extraction, this cheat sheet has you covered! 🧠✨