Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

๐Ÿ“š A practical approach to machine learning.

License

Notifications You must be signed in to change notification settings

singlav/practicalAI

Repository files navigation

A practical approach to machine learning.

Created by Goku Mohandas and contributors

Notebooks

  • ๐ŸŒŽ โ†’ https://madewithml.com
  • ๐Ÿ“š Illustrative ML notebooks in TensorFlow 2.0 + Keras.
  • โš’๏ธ Build robust models using the functional API w/ custom components
  • ๐Ÿ“ฆ Train using simple yet highly customizable loops to build products fast
  • If you prefer Jupyter Notebooks or want to add/fix content, check out the notebooks directory.

Basic ML

Basics Machine Learning Tools Deep Learning
  • Learn Python basics with notebooks.
  • Use data science libraries like NumPy and Pandas.
  • Implement basic ML models in TensorFlow 2.0 + Keras.
  • Create deep learning models for improved performance.
๐Ÿ““ Notebooks ๐Ÿ“ˆ Linear Regression ๐Ÿ”Ž Data & Models ๏ธ๐Ÿ–ผ Convolutional Neural Networks
๐Ÿ Python ๐Ÿ“Š Logistic Regression ๐Ÿ›  Utilities ๐Ÿ‘‘ Embeddings
๐Ÿ”ข NumPy ๏ธ๐ŸŽ› Multilayer Perceptrons ๏ธโœ‚๏ธ Preprocessing ๐Ÿ“— Recurrent Neural Networks
๐Ÿผ Pandas

Production ML

Local Applications Scale Miscellaneous
  • Setup your local environment for ML.
  • Wrap your ML in RESTful APIs using Flask to create applications.
  • Standardize and scale your ML applications with Docker and Kubernetes.
  • Deploy simple and scalable ML workflows using Kubeflow.
๐Ÿ’ป Local Setup ๐ŸŒฒ Logging ๐Ÿณ Docker ๐Ÿค Distributed Training
๐Ÿ ML Scripts โšฑ๏ธ Flask Applications ๐Ÿšข Kubernetes ๐Ÿ”‹ Databases
โœ… Unit Tests ๐ŸŒŠ Kubeflow ๐Ÿ” Authentication

Advanced ML

General Sequential Popular Miscellaneous
  • 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.
๐Ÿง Attention ๐Ÿ Transformers ๐ŸŽญ Generative Adversarial Networks ๐Ÿ”ฎ Autoencoders
๐ŸŽ๏ธ Highway Networks ๐Ÿ‘น BERT, GPT2, XLNet ๐ŸŽฑ Bayesian Deep Learning ๐Ÿ•ท๏ธ Graph Neural Networks
๐Ÿ’ง Residual Networks ๐Ÿ•˜ Temporal CNNs ๐Ÿ’ Reinforcement Learning

Topics

Computer Vision Natural Language Unsupervised Learning Miscellaneous
  • Learn how to use deep learning for computer vision tasks.
  • Implement techniques for natural language tasks.
  • Derive insights from unlabeled data using unsupervised learning.
๐Ÿ“ธ Image Recognition ๐Ÿ“– Text classification ๐Ÿก Clustering โฐ Time-series Analysis
๐Ÿ–ผ๏ธ Image Segmentation ๐Ÿ’ฌ Named Entity Recognition ๐Ÿ˜๏ธ Topic Modeling ๐Ÿ›’ Recommendation Systems
๐ŸŽจ Image Generation ๐Ÿง  Knowledge Graphs ๐ŸŽฏ One-shot Learning
๐Ÿ—ƒ๏ธ Interpretability

About

๐Ÿ“š A practical approach to machine learning.

Resources

License

Code of conduct

Contributing

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Jupyter Notebook 100.0%

AltStyle ใซใ‚ˆใฃใฆๅค‰ๆ›ใ•ใ‚ŒใŸใƒšใƒผใ‚ธ (->ใ‚ชใƒชใ‚ธใƒŠใƒซ) /