ahmedbelgacem/awesome-datascience

A curated list of awesome python, machine learning, computer vision and data science resources, articles, guides, courses and books.

Awesome-Datascience

This is mainly a curated list of awesome python, machine learning, computer vision and data science resources, articles, guides, courses and books. Since there's a lot of awesome lists for frameworks and libraries out there, I may add libraries, software and frameworks I find awesome but that's not the purpose of this list.
This list will follow me along my journey and I will be updating it as I progress. I'm making this list for my personal use mainly but I'm sharing it here if it may help anyone. Some of the courses are courses I had at my university that are available freely online.

• Awesome Data Science
  • AI and games
  • Computer Vision
  • Data Engineering
  • Deep Learning
  • Edge Computing
  • Exploratory Data Analysis
  • Fundamentals
  • Graph Neural Networks
  • Generative Learning
  • Information Retireval
  • Machine Learning
  • Mathematics
  • Natural Language Processing
  • Python
  • Pytorch
  • Reinforcement Learning
  • Statistics

AI and games:

• Intelligence artificielle, une approche ludique - Tristan Cazenave (French Book)

• Monte Carlo Search

  • Monte Carlo Search - Tristan Cazenave

Computer Vision:

• Classification:

  • An intuitive guide to deep network architectures

• Edge Detection:

  • Canny Edge Detection - Step by Step in Python
  • Quality Assessment Methods to Evaluate the Performance of Edge Detection Algorithms

• Object Detection:

  • Deep Learning Bible 4- Object Detection

• Semantic Segmentation:

  • A survey of loss functions for semantic segmentation

• Yolo:

  • Understand yolov8 structure
  • YOLOv8: One Concept You Must Know in Object Detection — Letterbox
  • The dumb reason your fancy Computer Vision app isn’t working: Exif Orientation

Data Engineering:

• Hadoop: The Definitive Guide
• Data-Intensive Text Processing with MapReduce

Deep Learning:

• Deep Learning Specialization - Andrew NG
• A Recipe for Training Neural Networks - Andrej Karpathy

• LSTM:

  • Understanding LSTM Networks
  • Illustrated Guide to LSTM’s and GRU’s: A step by step explanation

• Multi-Task Learning:

  • Deep Multi-Task Learning — 3 Lessons Learned
  • Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
  • Multi-Task Learning with Pytorch and FastAI
  • Multi Task Learning with Homoscedastic Uncertainty Implementation

• RNN:

  • Illustrated Guide to Recurrent Neural Networks

• SPP:

  • Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

Edge computing:

• Machine Learning Compilers, optimizers and Gpu accelerated deep learning:

  • A friendly introduction to machine learning compilers and optimizers
  • The Correct Way to Measure Inference Time of Deep Neural Networks

  • TensorRT:

    • Profiling Deep Learning Networks And Automatic Mixed Precision For Optimization

Exploratory Data Analysis:

• Principal component analysis, Correspondence Analysis, Multiple Correspondence Analysis:

  • Analyse des données - Patrice Bertrand et Denis Pasquignon (French Course)

Fundamentals:

• Docker:

  • Simplified guide to using Docker for local development environment
  • Use the same Dockerfile for both local development and production with multi-stage builds
  • Introduction to docker - Datacamp

• Git:

  • Introduction to Git for Data Science

• Web Scraping:

  • Web Scraping with Python

Graph Neural Networks:

• Machine Learning with Graphs - Stanford University
• LiteratureDL4Graph, A comprehensive collection of recent papers on graph deep learning

Generative Learning:

• Variational Autoencoders:

  • The theory behind Latent Variable Models: formulating a Variational Autoencoder
  • How to Generate Images using Autoencoders
  • MIT 6.S191 Introduction to Deep Learning Lecture 4: Deep Generative Modeling

• Diffusion Models:

  • Diffusion Theory
  • How diffusion models work: the math from scratch
  • Understanding Diffusion Models: A Unified Perspective

Information Retrieval:

• Introduction to Information Retrieval - Cambridge University, Christopher D. Manning, Prabhakar Raghavan and Hinrich Schütze

• Semantic Search:

  • Semantic Search - Sentence Transformers Documentation - A guide on using sbert for semantic search

Machine Learning:

• Machine Learning - Stanford University, Andrew NG
• Python Machine Learning, 3rd Edition - Sebastian Raschka , Vahid Mirjalili

• Boosting Algorithms:

  • Boosting algorithms explained
  • A Gentle Introduction to the Gradient Boosting Algorithm for Machine Learning

• Preparing for a machine learning interview:

  • Introduction to Machine Learning Interviews

  • Machine Learning System Design:

    • Designing Machine Learning Systems: An Iterative Process for Production-Ready Applications - Chip Huyen

• Support Vector Machines:

  • Support Vector Machines (SVM) - An overview

Mathematics:

• Optimization for Machine Learning:

  • Optimization for Machine Learning - Clément Royer

Natural Language Processing:

• Transformers:

  • Attention is all you need
  • Hugging Face Course

Python:

• Learning Python: Powerful Object-Oriented Programming - Mark Lutz

• Clean Code:

  • How to write beautiful python code with PEP 8
  • 5 Different Meanings of Underscore in Python
  • f-Strings: A New and Improved Way to Format Strings in Python
  • The Zen of Python
  • Google Python Style Guide
  • PEP8 online checker

• Data Structures:

  • Binary Tree
  • Binary Search Tree
  • Queue in Python
  • Sets in Python

• Distribution:

  • How to create a Python library
  • How to upload your python package to PyPi

• Documentation:

  • Python Docstrings
  • Auto-documenting a python project using Sphinx

• Efficient Code:

  • Code Profiling
  • Python's Counter: The Pythonic Way to Count Objects
  • Unpacking in Python
  • Using the Python zip() Function for Parallel Iteration

• Generators:

  • Python yield, Generators and Generator Expressions
  • How to Use Generators and yield in Python

• Metaclasses:

  • Python Metaclasses

• Tools and development environements:

  • Jupyter Notebook

    • 7 essential tips for writing with jupyter notebook

• Preparing for a coding interview:

  • CP-Algorithms.com
  • Competitive Programmer’s Handbook - Antti Laaksonen (2018)
  • Grokking LeetCode: A Smarter Way to Prepare for Coding Interviews
  • Interview School
  • Introduction to Algorithms, 3rd Edition
  • Pramp - Mock interviews with peers

  • Algorithms:

    • Dynamic Programming
    • Greedy Algorithms

  • Python implementation for different coding problem patterns:

    • Coding Patterns: In-place Reversal of a Linked List
    • 4 types of tree traversal algorithms (Java implementation)
    • Coding Patterns: Depth First Search (DFS)
    • Coding Patterns: Breadth First Search (BFS)

Pytorch:

• Pytorch 101: An applied tutorial
• Faster Deep Learning Training with PyTorch – a 2021 Guide

Reinforcement Learning:

• Reinforcement Learning An Introduction - Richard S.Sutton, Andrew G. Barto
• Reinforcement Learning - Stéphane Airiau (French Course)

Statistics:

• Estimation, Confidence Interval, Hypothesis Testing:

  • Statistique mathématique - Vincent Rivoirard (French Course)
  • The Bootstrap Method for Standard Errors and Confidence Intervals

• Monte Carlo Method:

  • Méthodes de Monte Carlo - Julien Stoehr (French Course)