📚 Learning Resources
Everything you need to learn ML: datasets, tools, tutorials, cheatsheets, and book recommendations.
Datasets
MNIST
Digit Classification
70K images
CIFAR-10
Image Classification
60K images
ImageNet
Image Classification
14M images
IMDB Reviews
Sentiment Analysis
50K texts
SQuAD 2.0
Question Answering
150K QA pairs
COCO
Object Detection
330K images
MovieLens
Recommendation
25M ratings
Kaggle Titanic
Binary Classification
1.3K rows
Tools & Libraries
TensorFlow
Google's ML framework
PyTorch
Facebook's ML framework
Scikit-learn
Classical ML algorithms
Hugging Face
Transformers & models
Pandas
Data manipulation
NumPy
Numerical computing
Matplotlib
Data visualization
Weights & Biases
Experiment tracking
MLflow
ML lifecycle management
Docker
Containerization
FastAPI
API development
Streamlit
ML app deployment
Tutorials & Guides
Neural Network from Scratch
Build a neural network using only NumPy to truly understand backpropagation.
Fine-tuning BERT
Step-by-step guide to fine-tune BERT for text classification.
Deploy ML Model with FastAPI
Create a REST API for your trained model and deploy to cloud.
CNN Visualization Techniques
Understand what CNNs learn using Grad-CAM and feature visualization.
Hyperparameter Tuning with Optuna
Automate hyperparameter search for better model performance.
Building RAG Applications
Create retrieval-augmented generation systems with LangChain.
Cheatsheets
NumPy Cheatsheet
2 pages • 15K downloads
Pandas Cheatsheet
2 pages • 18K downloads
Matplotlib Cheatsheet
2 pages • 12K downloads
Scikit-learn Cheatsheet
4 pages • 20K downloads
PyTorch Cheatsheet
3 pages • 14K downloads
TensorFlow Cheatsheet
3 pages • 11K downloads
SQL for ML Cheatsheet
2 pages • 9K downloads
Git for ML Cheatsheet
1 pages • 8K downloads
Recommended Books
Hands-On Machine Learning
Aurélien Géron
Deep Learning
Goodfellow, Bengio, Courville
Pattern Recognition and ML
Christopher Bishop
Python Machine Learning
Sebastian Raschka