Documentation - Basic Tutorials

The Basics - Level 1

• Creating Our First Model (Training, Prediction And Debugging)

• Saving And Loading Model Parameters (Training And Prediction Continuation)

The Basics - Level 2

• Using Solvers (Training Methods)

• Using Optimizers (Training Speed-Up)

• Using Regularizers (Dirty / Noisy Data Handling)

• Using Training Modifiers (Data Subset Training)

• Using Model Checker (Testing And Validation)

The Basics - Level 3

• Distributed Training (Server-To-Server, Client-To-Server And Client-To-Client Training)

Data Transformation

• Redundant Models

The Neural Networks

• Using Neural Networks, Part 1

• Using Neural Networks, Part 2

• General Guide For Neural Networks Settings

Learning AIs - Level 1

• Introduction To Reinforcement Learning

• Choosing The Most Effective Environment Inputs

• Self-Learning Sword-Fighting AIs Using Dicrete Action Space

Learning AIs - Level 2

• Using Random Network Distillation (Simulating Curiosity)

• Using Eligibility Traces (Improving Action-Reward Association For Discrete Action Space)

• Self-Learning Car Using Continuous Action Space

Learning AIs - Level 3

• Deep Reinforcement Learning Algorithms Properties

• Multi-Agent Reinforecement Learning Setup