Made With ML · Lessons

🔥 We're among the top 10 ML repos on GitHub

Build your portfolio

As you learn ML, it's important to work on projects, so check out Made With ML for inspiration and to create a profile to showcase your own projects!

🔍 Discover ML projects with code on niche topics that interest you.
🛠 Build projects of your own and share it with the community.
👩‍💻 Showcase your profile on your resume or apply directly to ML managers.

NOTE: For those looking for careers in ML, everyone has Coursera, Kaggle, fasti on their resumes, so how are you differentiating yourself? Check out this post on how to stand out with an MWML profile.

Notebooks

📚 Illustrative ML notebooks available in both TensorFlow 2.0 + Keras and PyTorch.
- Should I pick TensorFlow or PyTorch? Choice of framework doesn’t matter! Check out the basic lessons and choose what you find more intuitive/suitable but the most important thing is to work on projects (and share them on Made With ML so the community can benefit and you can create an awesome portfolio to share).
- Do I need to know both TensorFlow or PyTorch? It is very important to at least know how to read both frameworks because cutting edge research continues to use both frameworks. Luckily, they're both very easy to learn and very easy to rewrite in the other framework.
Talk about why you need to at least be able to read both these days. Great research that continues to use both frameworks and it’s very easy to learn and very easy to rewrite in the other framework.
💻 These are not a set of tutorials where we just load a bunch of packages and apply it on preloaded datasets. We explain every concept in the notebooks with clean code, simple math and visualizations to make them as intuitive as possible.
📆 Typical release cadence will be one new notebook topic per week (starting April 2020).
📓 If you prefer Jupyter Notebooks or want to add/fix content, check out the notebooks directory.

Foundation

Learn Python basics with notebooks. Use data science libraries like NumPy and Pandas. Learn the basics of deep learning frameworks like TensorFlow and PyTorch.	📓 Notebooks	🔢 NumPy	TensorFlow
	🐍 Python	🐼 Pandas	PyTorch

Basics

Implement basic ML models in TensorFlow 2.0 + Keras or PyTorch. Create deep learning models for improved performance.	📈 Linear Regression \|	🔎 Data & Models \|	️🖼 Convolutional Neural Networks \|
	📊 Logistic Regression \|	🛠 Utilities \|	👑 Embeddings \|
	️🎛 Multilayer Perceptrons \|	️✂️ Preprocessing \|	📗 Recurrent Neural Networks \|

APIs

Setup your local environment for ML. Wrap your ML in RESTful APIs using Fast API to create applications.	💻 Local Setup	✅ Unit Tests	🏎 Fast API
	🐍 ML Scripts	🌲 Logging	📝 Swagger

Full-stack

Learn how to collect data and organize it using SQL.
Showcase your applications using a simple Boostrap front-end.

🌍 Web scraping

🔋 SQL

🎨 Bootstrap

Scaling

Standardize and scale your ML applications with Docker and Kubernetes.
Deploy simple and scalable ML workflows using MLFlow.

🐳 Docker

🚢 Kubernetes

🌊 MLFlow

Advanced

Dive into architectural and interpretable advancements in neural networks. Implement state-of-the-art NLP techniques. Learn about popular deep learning algorithms used for generation, time-series, etc.	🧐 Attention	🎭 Generative Adversarial Networks	🔮 Autoencoders
	📘 Language Modeling	🎱 Bayesian Deep Learning	🕷️ Graph Neural Networks
	🤗 Transformers	🍒 Reinforcement Learning	🎯 One-shot Learning
	🤯 SHA-RNN	🐙 Causal Inference	⏱ Temporal CNNs

Topics

Learn how to use deep learning for computer vision tasks. Implement techniques for natural language tasks. Derive insights from unlabeled data using unsupervised learning.	📸 Image Recognition	📖 Text classification	🍡 Clustering
	🖼️ Image Segmentation	💬 Named Entity Recognition	🏘️ Topic Modeling
	🎨 Image Generation	🧠 Knowledge Graphs	🕵️ Anomaly Detection

Miscellaneous

Learn about miscellaneous topics that are at the forefront of ML research and application.	⏰ Time-series	🗃️ Interpretability	⚖️ Imbalanced Datasets
	🎤 Speech Recognition	✍️ Data Annotation	👻 Missing Values
	🛒 Recommendation Systems	✂️ Model Compression	📊 Data Visualization

Statistical Learning

Learn the basics of statistics that paved the way for all the topics above. Implement statistical learning methods in scikit-learn.	🧪 Hypothesis Testing	📈 Linear Regression	🏘 Nearest Neighbors	🥅 Matrix Decomposition
	❤️ Maximum Likelihood Estimation	📊 Logistic Regression	🍿 Gaussian Processes	🎒 Ensembles
	👶 Naive Bayes	🦺 Support Vector Machines	🎩 Hidden Markov Models

Implement basic ML models in TensorFlow 2.0 + Keras or PyTorch. Create deep learning models for improved performance.	📈 Linear Regression \|	🔎 Data & Models \|	️🖼 Convolutional Neural Networks \|
	📊 Logistic Regression \|	🛠 Utilities \|	👑 Embeddings \|
	️🎛 Multilayer Perceptrons \|	️✂️ Preprocessing \|	📗 Recurrent Neural Networks \|

StoneLiu/lessons