100DaysOfAIEngineer

📝 Curated Blog Articles for 100 Days of AI Engineer

A comprehensive collection of high-quality blog posts and tutorials for each topic in the curriculum, carefully researched and selected for 2024-2025.

---

📊 Phase 1: Foundations & Classical ML (Days 1-15)

NumPy (Days 1-2)

🔥 Must-Read Articles:

1. The Ultimate NumPy Tutorial for Data Science Beginners - Analytics Vidhya
   • Comprehensive tutorial covering NumPy from basics to advanced topics
   • Includes image data manipulation
   • Updated for 2025
2. Python NumPy Arrays Tutorial in 2025 - Bacancy Technology
   • Latest 2025 tutorial with modern practices
   • Covers data science applications
   • Updated December 2024
3. NumPy for Absolute Beginners - Towards Data Science
   • Project-based learning approach
   • Mini projects for hands-on practice
   • Published within last week
4. Python Data Science Handbook - NumPy - Jake VanderPlas
   • Classic comprehensive reference
   • Free online book chapter
   • Industry standard resource

---

Pandas (Days 3-4)

🔥 Must-Read Articles:

1. Python Pandas Tutorial: A Complete Guide for Beginners - Around Data Science
   • Pandas as “the ultimate tool for data manipulation”
   • Covers Series, DataFrames, cleaning, transformation
   • Complete beginner-friendly guide
2. Mastering Data Manipulation with Python Pandas - Medium
   • Comprehensive guide with advanced techniques
   • Performance optimization tips
   • Hands-on examples
3. How to Manipulate Data Using Pandas - Analytics Vidhya
   • Versatile toolkit for structured data
   • Crucial for data scientists and analysts
   • Practical examples
4. Practical Tutorial on Data Manipulation - HackerEarth
   • Hands-on practical approach
   • Covers both NumPy and Pandas
   • Intuitive syntax explanations
5. Pandas Tutorial - GeeksforGeeks
   • Complete reference documentation
   • Grouping and aggregating techniques
   • Data processing and normalization

---

Machine Learning Fundamentals (Days 8-14)

🔥 Must-Read Articles:

1. A Comprehensive Guide to Scikit-Learn - Medium
   • Decision trees, SVMs, k-NN implementations
   • Code examples included
   • Production-ready practices
2. Scikit-Learn Tutorial: Machine Learning in Python - Dataquest
   • Uses Naive-Bayes, LinearSVC, K-Neighbors
   • Practical sales data examples
   • Performance comparison
3. Python Machine Learning: Scikit-Learn Tutorial - DataCamp
   • Supervised and unsupervised learning
   • Consistent interface across algorithms
   • NumPy arrays and DataFrames
4. Machine Learning Algorithm Recipes - Machine Learning Mastery
   • 5 recipes for supervised classification
   • Standard datasets
   • Practical implementations

---

Linear Regression & Gradient Descent (Days 8-9)

🔥 Must-Read Articles:

1. Linear Regression using Gradient Descent - Medium (TDS Archive)
   • How gradient descent works from scratch
   • Loss function definition
   • Python implementation
2. Implementing Linear Regression with Gradient Descent From Scratch - Towards Data Science
   • Derives gradient descent from ground up
   • Single class with Python and NumPy
   • Step-by-step fashion
3. Gradient Descent in Linear Regression - GeeksforGeeks
   • Optimization algorithm explained
   • Gradually adjusting slope and intercept
   • Minimizing errors step by step
4. Gradient descent from scratch in Python - Dmitrijs Kass
   • Object-oriented approach
   • Forward and backward propagation
   • Complete implementation
5. How to Implement Linear Regression From Scratch - Machine Learning Mastery
   • Stochastic gradient descent
   • Scratch implementation
   • Python tutorial

---

🧠 Phase 2: Deep Learning Fundamentals (Days 16-30)

Neural Networks & Backpropagation (Days 16-19)

🔥 Must-Read Articles:

1. A Comprehensive Guide to the Backpropagation Algorithm - Neptune.ai
   • Most widely used training algorithm
   • Mathematical examples
   • Python coding implementations
2. A Step by Step Backpropagation Example - Matt Mazur
   • Concrete example with actual numbers
   • Python implementation on GitHub
   • Classic must-read tutorial
3. Mastering Backpropagation - DataCamp
   • Hands-on image classification
   • MNIST dataset implementation
   • Training and evaluation
4. How Does Backpropagation Work? - Built In
   • Error rates feed back through network
   • Neural network training process
   • Beginner-friendly explanation
5. Backpropagation Step by Step - hmkcode
   • Detailed colorful steps
   • Concrete example walkthrough
   • Visual explanations
6. Understanding Backpropagation Algorithm - Medium (TDS)
   • Chain rule of calculus
   • Gradient computation
   • Iterative weight updates

---

PyTorch (Days 20-21)

🔥 Must-Read Articles:

1. How to Learn PyTorch From Scratch in 2025 - DataCamp
   • Expert guide with 8-week learning plan
   • Step-by-step tutorials
   • Published November 2024
2. Why You Should Learn PyTorch in 2025 - OpenCV
   • Positioning at ML/AI innovation forefront
   • Python-based ecosystem
   • Dynamic computation capabilities
   • Published February 2025
3. PyTorch for Deep Learning - Dataquest
   • “PyTorch has won the hearts of AI developers”
   • O’Reilly Technology Trends 2025
   • Published May 2025
4. PyTorch Tutorial: Create and Train a Basic Neural Network - Medium
   • Learn PyTorch in 10 Notebook Code Cells
   • Free GPU via Kaggle
   • Published September 2024
5. Zero to Mastery Learn PyTorch - LearnPyTorch.io
   • Complete online book
   • Foundations of ML and DL
   • Free comprehensive resource
6. PyTorch Official Tutorials - PyTorch.org
   • Official documentation
   • 60-minute blitz for quick start
   • Learn the basics tutorial

---

👁️ Phase 3: Computer Vision (Days 31-45)

Convolutional Neural Networks (Days 23-26)

🔥 Must-Read Articles:

1. Convolutional Neural Networks for Dummies - Medium
   • Inspired by biological visual cortex
   • Step-by-step CNN tutorial
   • Image recognition and processing
2. Introduction to Convolutional Neural Networks - DataCamp
   • Specialized deep learning algorithm
   • Object recognition tasks
   • Hands-on TensorFlow tutorials
3. ELI5 Guide to CNNs - Saturn Cloud
   • Reduces images to easier form
   • Critical features preserved
   • Beginner-friendly explanations
4. Stanford CS231n: Convolutional Networks - Stanford
   • Academic gold standard
   • Conv Layer, Pooling, FC layers
   • In-depth technical explanations
5. Keras CNN Tutorial - Victor Zhou
   • Beginner-friendly implementation
   • Keras for image classification
   • Practical code examples

---

Transfer Learning (Days 25-26)

🔥 Must-Read Articles:

1. Transfer Learning for Computer Vision Tutorial - PyTorch Official
   • Train CNN using transfer learning
   • ResNet18 for ants and bees
   • Small dataset techniques
2. Deep Learning CV using Transfer Learning (ResNet-18) - Medium
   • Medical imaging application
   • Customizing ResNet
   • Skin cancer classification
3. Transfer Learning in Keras - ML Mastery
   • VGG, Inception, ResNet models
   • Convenient access via Keras
   • Practical implementations
4. A Guide to Transfer Learning with Keras using ResNet50 - Medium
   • Step-by-step ResNet50 guide
   • Keras implementation
   • Pre-trained weights usage
5. Car Model Classification with Transfer Learning - Statworx
   • Real-world application
   • TensorFlow 2.x
   • Overview of ResNet architecture
6. Transfer Learning Guide - Neptune.ai
   • Images and text in Keras
   • ResNet and Xception architectures
   • Pre-trained weights with Keras

---

YOLO Object Detection (Days 32-34)

🔥 Must-Read Articles:

1. YOLO Object Detection Explained: A Beginner’s Guide - DataCamp
   • Understanding YOLO fundamentals
   • Benefits and evolution
   • Real-life applications
2. YOLO Algorithm for Object Detection - V7 Labs
   • Powers ChatGPT and applications
   • Complete algorithm explanation
   • Examples included
3. Object Detection with YOLO: Hands-on Tutorial - Neptune.ai
   • TensorFlow/Keras implementation
   • Custom training
   • Latest YOLO11 coverage
4. Implementing YOLO v3 from Scratch in PyTorch - Paperspace
   • Network architecture from config
   • Load weights and design pipelines
   • Complete PyTorch implementation
5. Real-Time Object Detection Using YOLOv8 - E2E Networks
   • Step-by-step walkthrough
   • Setup, training, deployment
   • Latest YOLOv8 version
6. YOLO Object Detection with OpenCV - PyImageSearch
   • Using OpenCV and Python
   • Images and video detection
   • Deep Learning integration
7. How to Perform Object Detection With YOLOv3 in Keras - ML Mastery
   • Keras implementation
   • Detection on new photographs
   • Step-by-step guide

---

Image Segmentation (Days 35-36)

🔥 Must-Read Articles:

1. U-Net Image Segmentation in Keras - PyImageSearch
   • Encoder-decoder with skip connections
   • U-shaped architecture
   • Keras implementation
2. U-Net: Training Image Segmentation Models in PyTorch - PyImageSearch
   • PyTorch implementation
   • Complete training pipeline
   • Medical imaging focus
3. U-Net Architecture For Image Segmentation - DigitalOcean
   • Designed for biomedical images
   • Satellite and autonomous driving
   • Limited training data performance
4. Keras: Image Segmentation with U-Net-like Architecture - Keras Official
   • Official Keras tutorial
   • Oxford Pets dataset
   • Production-ready code
5. U-net Unleashed: Step-by-Step Guide - Medium
   • TensorFlow implementation
   • Training from scratch
   • Real-world data application
6. U-Net: A Versatile Architecture - Medium
   • Architecture overview
   • Multiple applications
   • Implementation guide

---

💬 Phase 4: Natural Language Processing (Days 46-60)

NLP Fundamentals (Days 46-52)

🔥 Must-Read Articles:

1. How to Learn NLP From Scratch in 2025 - DataCamp
   • Expert guide with step-by-step plan
   • Week-by-week learning roadmap
   • Published September 2024
2. Comprehensive NLP Learning Path 2025 - Analytics Vidhya
   • Months 2-3: Text processing, embeddings
   • Months 4-5: GPT, transfer learning
   • LangChain and Hugging Face
   • Published December 2024
3. Natural Language Processing Tutorial - GeeksforGeeks
   • Speech recognition to translation
   • Text summarization applications
   • Published July 2025
4. Beginner’s Guide to NLP with Python - ML Mastery
   • Text preprocessing essentials
   • NLTK implementation
   • Lemmatization, POS tagging, NER
   • Published November 2024
5. Top 20 NLP Projects for Beginners - Emeritus
   • Beginner to professional projects
   • Practical applications
   • Published June 2025

---

Word Embeddings (Days 48-49)

🔥 Must-Read Articles:

1. Word2Vec For Word Embeddings - A Beginner’s Guide - Analytics Vidhya
   • Revolutionized NLP
   • Dense vector representations
   • CBOW and Skip-gram models
2. A Dummy’s Guide to Word2Vec - Medium
   • Easy training with Gensim
   • Complete Colab notebook
   • Practical examples
3. Word2vec from Scratch - Jake Tae
   • From-scratch implementation
   • Forward/backward propagation
   • “king - man + woman = queen”
4. Word Embedding using Word2Vec - GeeksforGeeks
   • Python with Gensim
   • Building word vector models
   • Both CBOW and Skip-Gram
5. NLP Illustrated: Word2Vec - Towards Data Science
   • Math behind embeddings
   • Pre-trained leveraging
   • Gensim implementation

---

BERT & Transformers (Days 55-58)

🔥 Must-Read Articles:

1. BERT 101 - State Of The Art NLP Model - Hugging Face
   • ML model for NLP (2018 Google AI)
   • Easy tutorial in Google Colab
   • Official Hugging Face guide
2. Practical Introduction to Transformer Models: BERT - Towards Data Science
   • Fine-tune for sentiment analysis
   • Complete code on GitHub
   • Jupyter Notebook available
3. A Visual Guide to Using BERT - Jay Alammar
   • Simple tutorial for sentence classification
   • Notebook on Colab and GitHub
   • Visual explanations
4. The Illustrated BERT - Jay Alammar
   • How NLP cracked transfer learning
   • Featured in Stanford, Harvard, MIT courses
   • Visual, intuitive explanations
5. How to Code BERT Using PyTorch - Neptune.ai
   • What BERT is and how it works
   • PyTorch implementation
   • Tutorial with examples
6. Mastering BERT: Beginner to Advanced - Medium
   • Complete journey through BERT
   • Explanations and code snippets
   • Comprehensive guide
7. BERT Architecture Explained - Analytics Vidhya
   • Architecture overview
   • Input and output of BERT
   • Needs and applications

---

Attention Mechanism (Days 55-56)

🔥 Must-Read Articles:

1. The Illustrated Transformer - Jay Alammar ⭐⭐⭐
   • Featured in Stanford, Harvard, MIT, CMU
   • Most popular transformer explanation
   • Multi-headed attention visualizations
   • Self-attention mechanism
2. Understanding and Coding Self-Attention From Scratch - Sebastian Raschka
   • Original scaled dot-product attention
   • Most widely used in practice
   • Complete from-scratch implementation
   • Published February 2023
3. Creating a Transformer From Scratch: Attention Mechanism - Mixed Precision
   • Write Attention layer in PyTorch
   • Bidirectional, Causal, Cross Attention
   • All three flavors covered
4. Tutorial 6: Transformers and Multi-Head Attention - UvA DL Notebooks
   • Academic tutorial
   • Scaled dot product attention
   • Multi-head attention explanation
5. Complete Guide to Transformer Architecture - TensorGym
   • Mathematical formulation
   • Attention(Q, K, V) = softmax(QK^T/√d)V
   • From theory to implementation
   • Published 3 days ago
6. The Transformer Attention Mechanism - ML Mastery
   • Foundational concepts
   • Step-by-step explanation
   • Practical implementation

---

Hugging Face Transformers (Days 57-59)

🔥 Must-Read Articles:

1. Fine-tuning a pretrained model - Hugging Face Official
   • Adapts to specific tasks
   • Less data and compute required
   • Trainer API comprehensive guide
   • Yelp reviews classification
2. Fine-Tuning Your First LLM with PyTorch and Hugging Face - Hugging Face
   • Microsoft Phi-3 Mini fine-tuning
   • English to Yoda-speak translation
   • Practical implementation
3. How to Fine-Tune LLMs in 2024 - Phil Schmid
   • Using Hugging Face TRL
   • Text to SQL dataset
   • Transformers and Datasets
4. Harnessing NLP Superpowers: Fine Tuning Tutorial - Analytics Vidhya
   • Step-by-step guide
   • NLP superpowers unlocked
   • Practical examples
5. Fine-Tuning BERT - FutureSmart AI
   • Most widely used pre-trained model
   • Hugging Face implementation
   • Complete tutorial
6. Train and Fine-Tune Sentence Transformers - Hugging Face
   • Semantic search tasks
   • Sentence-level embeddings
   • Training guide

---

🤖 Phase 5: Large Language Models & RAG (Days 61-75)

Large Language Models (Days 61-68)

🔥 Must-Read Articles:

1. Large Language Models: What You Need to Know in 2025 - HatchWorks AI
   • Complete 2025 LLM guide
   • Latest developments
   • Production deployment
2. Mastering Large Language Models: A Learning Path - Turing
   • Transformer architectures
   • For AI engineers and beginners
   • Pretraining and fine-tuning
3. The Roadmap for Mastering Language Models in 2025 - ML Mastery
   • LLM University by Cohere
   • Sequential and non-sequential paths
   • RAG and LangChain coverage
4. Large Language Models: A Self-Study Roadmap - KDnuggets
   • Market: $6.4B (2024) → $36.1B (2030)
   • Structured stepwise approach
   • Concepts to deployment
5. What Are Large Language Models? Beginner’s Guide 2025 - KDnuggets
   • Predict and generate human-like text
   • Billions of parameters
   • Q&A, summarization, creative writing
6. GitHub: llm-course - mlabonne
   • LLM Scientist track
   • LLM Engineer track
   • Colab notebooks and roadmaps
7. Large Language Model Tutorial Series: 30 Lessons - Medium
   • BERT, GPT, RoBERTa, T5, DistilBERT
   • Step-by-step lessons
   • Free comprehensive series
8. Fine-Tuning LLMs: A Guide With Examples - DataCamp
   • Tailoring to specific tasks
   • Enhancing performance
   • Broadening applicability

---

Fine-Tuning LLMs with LoRA/QLoRA (Days 65-66)

🔥 Must-Read Articles:

1. In-depth Guide to Fine-tuning with LoRA and QLoRA - Mercity.ai
   • PEFT (Parameter Efficient Fine Tuning)
   • Reduces trainable parameters
   • QLoRA fixes quantization errors
2. Efficient Fine-Tuning with LoRA - Databricks
   • Implemented in Hugging Face PEFT
   • bitsandbytes integration
   • 4-bit quantized weights
3. Fine Tuning LLM: PEFT — LoRA & QLoRA - Medium
   • Part 1 of comprehensive series
   • Most widely used PEFT methods
   • Practical implementations
4. Parameter-Efficient Fine-Tuning with LoRA and QLoRA - Analytics Vidhya
   • Low-rank matrices injection
   • Reduces computational burden
   • Maintains or improves performance
5. Fine-Tuning Open-Source LLM using QLoRA with MLflow - MLflow
   • Hands-on with code examples
   • QLoRA with PEFT configuration
   • Few lines of code
6. Fine-Tuning LLaMA 2 using QLoRA and Single GPU - OVHcloud
   • 4-bit quantization
   • Low-Rank Adapters
   • Single GPU tutorial
7. LoRA and QLoRA: Effective Fine-tuning Methods - Medium
   • Detailed explanations
   • Memory reduction benefits
   • Training cost savings

---

RAG (Retrieval-Augmented Generation) (Days 71-73)

🔥 Must-Read Articles:

1. Build a Retrieval Augmented Generation (RAG) App - LangChain Official
   • Q&A over unstructured text
   • ~40 lines of code
   • Simple indexing and RAG chain
2. What is RAG? - DataCamp
   • Combines retrieval and generation
   • Authoritative knowledge base
   • Response optimization
3. Code a Simple RAG from Scratch - Hugging Face
   • Python and ollama
   • Key RAG components
   • In-memory vector database
4. A Complete Guide to RAG - Domo
   • Comprehensive overview
   • Production considerations
   • Best practices
5. RAG Basics: Basic Implementation - Medium
   • Three key components
   • Indexing, retrieval, generation
   • Step-by-step guide
6. Introduction to RAG - Weaviate
   • External knowledge sources
   • Prompt templates
   • Popular frameworks (LangChain, LlamaIndex)
7. What is RAG? - AWS
   • Optimizing LLM output
   • Training data augmentation
   • Enterprise applications
8. Retrieval-Augmented Generation - Pinecone
   • Example notebooks
   • Pinecone Assistant
   • Production-grade apps
9. GitHub: RAG Techniques - NirDiamant
   • Advanced RAG techniques
   • Information retrieval + generative models
   • Accurate contextual responses
10. Practical Tips for RAG - Stack Overflow
    • Evaluation pipelines
    • Search metrics (DCG, nDCG)
    • LLM-as-a-judge approaches

---

LangChain (Days 67-68)

🔥 Must-Read Articles:

1. LangChain Tutorial: Building LLM-Powered Apps - Elastic Blog
   • Step-by-step from scratch
   • Easy to build with existing LLMs
   • Complete implementation guide
2. How to Build LLM Applications with LangChain - DataCamp
   • Open-source framework
   • Suite of tools and components
   • Interfaces for LLM development
3. Build a RAG agent with LangChain - LangChain Official
   • Official tutorial
   • Q&A over text data
   • RAG techniques
4. Beginner’s Guide to LangChain - DEV Community
   • LLM-powered applications
   • Step-by-step guide
   • Real-time implementations
5. Building a Simple LLM Application with LangChain - Scalable Path
   • Framework simplifies process
   • Tutorial with examples
   • Production considerations
6. Build an LLM app with Streamlit - Streamlit
   • LangChain + Streamlit
   • Text generation
   • Interactive applications
7. Beginner’s Guide to LangChain - SingleStore
   • Real-time AI applications
   • SingleStore + LangChain
   • Database integration
8. Building LLM Applications: Hands-On Guide - PrepVector
   • Setting up LangChain
   • Chains, memory, retrieval
   • Output parsing
9. How to Use LangChain to Build With LLMs - freeCodeCamp
   • Fundamentals of LLMs
   • Python library
   • Popular framework guide

---

Vector Databases (Days 69-70)

🔥 Must-Read Articles:

1. Chroma DB Tutorial: Step-By-Step Guide - DataCamp
   • Open-source vector store
   • Store and retrieve embeddings
   • LLM metadata management
2. Beginner’s Guide: Pinecone, FAISS & Chroma - Medium
   • Three major vector databases
   • Powers semantic search
   • ChatGPT applications
3. Chroma DB vs Pinecone vs FAISS - RisingWave
   • Detailed comparison
   • AI applications focus
   • Performance benchmarks
4. Chroma vs Pinecone: Project Selection - MyScale
   • Different use cases
   • Project requirements
   • Selection criteria
5. Experimenting with Vector Databases - Medium
   • ChromaDB, Pinecone, Weaviate, Pgvector
   • Hands-on experiments
   • Practical comparisons
6. Building Vector Search Engine - Medium
   • Pinecone, ChromaDB, Faiss
   • Using LangChain
   • Powerful search implementation
7. The 7 Best Vector Databases in 2025 - DataCamp
   • Comprehensive comparison
   • Latest options for 2025
   • Selection guide
8. Semantic Search with Vector Databases - Langformers
   • FAISS, ChromaDB, Pinecone
   • Semantic search implementation
   • Practical tutorial

---

🚀 Phase 6: MLOps & Production (Days 76-85)

MLOps Fundamentals (Days 76-85)

🔥 Must-Read Articles:

1. Getting Started With MLOps in 2024 - IGMGuru
   • Latest MLOps practices
   • 2024 best practices
   • Complete beginner guide
2. Introduction to MLOps - Carnegie Mellon SEI
   • Bridging ML and Operations
   • Critical AI discipline
   • Published November 2024
3. MLOps in 2025: Stay Competitive - HatchWorks
   • Hyper-automation trends
   • Autonomous workflows
   • 2025 developments
4. MLOps Roadmap 2025 - Scaler
   • $3.8B (2021) → $21.1B (2026)
   • Complete career guide
   • Step-by-step path
5. What Is MLOps? Developer’s Guide 2025 - Growin
   • 70% of enterprises operationalizing AI (Gartner)
   • Tools and automation
   • Monitoring in production
6. Mastering MLOps in 2024 - Medium
   • Comprehensive operations guide
   • 2024 best practices
   • Real-world examples
7. How to Learn MLOps in 2024 - Neptune.ai
   • Courses, books, resources
   • Great career move
   • Published September 2024
8. MLOps Roadmap - roadmap.sh
   • Visual learning path
   • Interactive roadmap
   • Community-driven
9. Machine Learning Operations For Beginners - Towards Data Science
   • Beginner-friendly introduction
   • Basic practices and tools
   • Hands-on project
10. MLOps For Beginners - Medium (TDS)
    • DVC for versioning
    • MLflow for tracking
    • FastAPI, Docker, AWS deployment

---

FastAPI for ML Deployment (Days 76-77)

🔥 Must-Read Articles:

1. Deploying ML Models with FastAPI and Heroku - TestDriven.io
   • Stock price prediction model
   • RESTful API on Heroku
   • Production deployment
2. Deploy ML Models Using FastAPI - Medium
   • Complete deployment guide
   • FastAPI implementation
   • Best practices
3. How to Use FastAPI for Machine Learning - PyCharm Blog
   • Penguin species classification
   • Nearest Neighbors algorithm
   • Query parameters API
4. FastAPI: Modern Toolkit for ML Deployment - Medium
   • Modern deployment approaches
   • Production-ready patterns
   • Best practices
5. ML Model Deployment with FastAPI and Docker - DEV Community
   • Accessible via RESTful API
   • Docker containerization
   • Complete walkthrough
6. ML Serving and Monitoring with FastAPI - EvidentlyAI
   • Complete deployment blueprint
   • Monitoring solutions
   • Open-source tools
7. Step-by-Step Guide: FastAPI and Docker - ML Mastery
   • Diabetes progression predictor
   • Scikit-learn dataset
   • Containerized API
8. Deploying ML Models Using FastAPI - Medium
   • RESTful deployment
   • Production patterns
   • Implementation guide
9. Deploy Deep Learning Models Step by Step - Analytics Vidhya
   • DL model serving
   • Step-by-step tutorial
   • FastAPI patterns
10. Build and Deploy ML Model with FastAPI - Towards Data Science
    • Wrapping models in REST API
    • Complete implementation
    • Production deployment

---

Docker for ML (Day 78)

🔥 Must-Read Articles:

1. Mastering Docker and Kubernetes for ML - DataCamp
   • Containerization power
   • Portability and scalability
   • Resource management
   • Kubernetes orchestration
2. Dockerizing Your ML Model: Step-by-Step - Medium
   • Package ML model with dependencies
   • Self-contained portable units
   • Complete guide
3. Containerize ML Workflow With Docker - Analytics Vidhya
   • Sentiment Analysis application
   • Push to DockerHub
   • Hands-on guide
4. Containerizing and Deploying ML Models - DEV Community
   • Scikit-learn and Iris dataset
   • Step-by-step tutorial
   • Practical examples
5. Containerization of ML Applications - Comet
   • Create, deploy, execute containers
   • Docker tool comprehensive guide
   • ML workflows
6. Why Docker for ML Development? - AWS Blog
   • Open source ML software challenges
   • Container benefits
   • Development best practices
7. Build and Run Docker Container for ML - Towards Data Science
   • Quick and easy build
   • Simple ML model
   • Container execution
8. Creating ML Model in Docker Container - Medium (Geek Culture)
   • Python in Docker
   • Model deployment
   • Complete workflow
9. Step-by-Step Guide to Deploying with Docker - KDnuggets
   • Consistent environment
   • Platform portability
   • Smoother deployment
10. GitHub: FriendlyDockerMLTutorial
    • Docker meets ML tutorial
    • Community resource
    • Hands-on examples

---

MLflow Experiment Tracking (Days 80-81)

🔥 Must-Read Articles:

1. A Swift Guide to MLFlow - Prophecy Labs
   • Open-source ML lifecycle platform
   • MLflow Tracking focus
   • Quick implementation
2. Getting Started with MLflow Tracking - Medium (MLearning.ai)
   • Streamline ML development
   • Organized experiment tracking
   • Beginner guide
3. Experiment Tracking in 10 Minutes - Towards Data Science
   • Components and terminologies
   • Python setup examples
   • Tracking and querying
4. ML Experiment Tracking Using MLflow - Analytics Vidhya
   • Open-source tracking tool
   • Model management
   • Code examples
5. Demystifying MLflow - Medium
   • Hands-on guide
   • Experiment tracking
   • Model registry
6. MLflow Official Tracking - MLflow Docs
   • Official documentation
   • Complete API reference
   • Best practices
7. MLflow 5-minute Quickstart - MLflow
   • Local Tracking Server
   • Log, register, load models
   • Quick implementation
8. Track Model Development Using MLflow - Databricks
   • Enterprise MLflow usage
   • Databricks integration
   • Production patterns
9. Experiment Tracking with MLflow - Medium
   • GitHub link included
   • Practical tutorial
   • Implementation examples
10. How We Track ML Experiments - Data Revenue
    • Real company experience
    • Production use cases
    • Best practices

---

Model Monitoring & Drift Detection (Day 82)

🔥 Must-Read Articles:

1. What is Data Drift in ML? - Evidently AI
   • Changes in feature distribution
   • Decline in performance
   • 20+ detection methods
   • Interactive visualizations
2. Guide To ML Monitoring And Drift Detection - BentoML
   • Monitoring importance
   • Statistical thresholds
   • Predicted distributions
   • Early warnings
3. How to Detect Model Drift - Towards Data Science
   • Real-time production data
   • Baseline comparison
   • Leading indicators
   • Troubleshooting tool
4. Productionizing ML: Deployment to Drift - Databricks
   • Monitor prediction quality
   • Statistical process control
   • Business control limits
   • Notification triggers
5. Monitoring NLP Models in Production - Evidently AI
   • Drug review dataset
   • Data quality issues
   • Debugging with Evidently
   • NLP-specific challenges
6. Understanding Data Drift and Model Drift - DataCamp
   • Why models drift
   • Different drift types
   • Detection algorithms
   • Python implementation
7. Identifying Drift in ML Models - Microsoft
   • Best practices
   • Consistent responses
   • Reliable predictions
   • Enterprise patterns
8. Model Drift: Identifying and Monitoring - Medium
   • Part I: Types of Drifts
   • ML Engineering focus
   • Production monitoring
   • Identification methods
9. Handling LLM Model Drift in Production - Rohan Paul
   • LLM-specific drift
   • Monitoring approaches
   • Retraining strategies
   • Continuous learning
10. 5 Methods to Detect Drift in ML Embeddings - Evidently AI
    • Embedding-specific drift
    • Detection techniques
    • Visual explanations
    • Implementation guide

---

📖 How to Use This Resource

For Each Day of Learning:

1. Start with the main curriculum (README.md or DAILY_BREAKDOWN.md)
2. Find your topic in this file
3. Read 2-3 articles marked with 🔥 (must-read)
4. Implement the concepts as you learn
5. Refer back when you need deeper understanding

Reading Strategy:

• Day 1-2 of a topic: Read introductory articles (marked as “Beginner”)
• Day 3-4: Read intermediate tutorials with code
• Day 5+: Dive into advanced articles and official documentation

Priority Levels:

• ⭐⭐⭐ Must-Read: Absolutely essential, industry-standard content
• 🔥 Highly Recommended: Best tutorials for the topic
• Regular: Good supplementary content

---

🔄 Keep This Updated

This list was researched in January 2025. The AI/ML field moves fast:

• Check publication dates
• Look for 2024-2025 articles when available
• Verify frameworks are still current
• Supplement with official documentation

---

💡 Tips for Effective Learning

1. Don’t read everything: Pick 2-3 articles per topic
2. Code along: Open a notebook and implement as you read
3. Take notes: Write down key insights
4. Compare approaches: Different authors have different perspectives
5. Check comments: Reader comments often have valuable tips
6. Bookmark favorites: Keep a list of articles you want to revisit

---

🤝 Contributing

Found a great article not listed here? Want to add one you wrote?

• Articles must be from 2023 or later (exceptions for classics)
• Must include working code examples or thorough explanations
• Should be freely accessible (no paywall beyond Medium’s limit)

---

Happy Learning! 🚀

Last Updated: January 2025 Research Date: January 13, 2025 Total Articles Curated: 150+