Seven new tutorials:

  • Introduction to TensorFlow and Keras application development
    • Zero, preface,
    • Introduction to Neural networks and deep learning
    • Second, model architecture
    • 3. Model evaluation and optimization
    • Fourth, productization
  • TensorFlow Practical guide to deep learning for images
    • Zero, preface,
    • Machine learning toolkit
    • 2. Picture data
    • Classical neural network
  • A practical guide to learning Python meta
    • Zero, preface,
    • Introduction to meta-learning
    • Face and audio recognition using connected networks
    • Prototype networks and their variants
    • Use TensorFlow relationships and matching networks
    • 5. Memory enhancement neural network
    • MAML and its variants
    • Meta-sgd and Reptile
    • 8. Gradient consistency as an optimization objective
    • Ix. Latest progress and follow-up steps
    • Ten, the answer
  • A practical guide to Python reinforcement learning
    • Zero, preface,
    • Introduction to reinforcement learning
    • Introduction to OpenAI and TensorFlow
    • Markov decision process and dynamic programming
    • Monte Carlo method for games
    • Five, time difference learning
    • Six, the multi-arm slot machine problem
    • 7. Deep learning foundation
    • Deep Q network and Atari games
    • 9. Play Doom with deep Loop Q Network
    • Asynchronous advantage Actor critic network
    • Strategy gradient and optimization
    • Capstone project — DQN for racing cars
    • Latest progress and follow-up steps
    • Xiv. Answer
  • Python Smart Project
    • Zero, preface,
    • First, the foundation of artificial intelligence system
    • Second, transfer learning
    • Neural machine translation
    • Fashion industry style transfer using GAN
    • 5. Video subtitle application
    • 6. Intelligent recommendation system
    • 7. Mobile app for movie review emotion analysis
    • Conversational AI chatbots for customer service
    • Autonomous autonomous vehicles using reinforcement learning
    • Captcha from the perspective of deep learning
  • Proficient in Sklearn and TensorFlow predictive analysis
    • Zero, preface,
    • Integration method of regression and classification
    • Two, cross verification and parameter adjustment
    • Three, the use of characteristics
    • Introduction to Artificial neural Networks and TensorFlow
    • Fifth, TensorFlow and deep neural network are used for predictive analysis
  • New features in TensorFlow 2.0
    • Zero, preface,
    • Part 1: TensorFlow 2.0 — Architecture and API changes
      • Introduction to TensorFlow 2.0
      • Keras default integration and eager implementation
    • Part 2: TensorFlow 2.0 – Data and model training pipeline
      • Design and build the input data pipeline
      • Iv. Model training and use of TensorBoard
    • Part 3: TensorFlow 2.0 — Model inference and deployment and AIY
      • 5. Model inference pipeline – Multi-platform deployment
      • AIY Project and TensorFlow Lite
    • Part 4: TensorFlow 2.0 – Migration, summary
      • Migrate from TensorFlow 1.x to 2.0