コース概要

Planner introduction

  • What is OptaPlanner?
  • What is a planning problem?
  • Use Cases and examples

Bin Packaging Problem Example

  • Problem statement
  • Problem size
  • Domain model diagram
  • Main method
  • Solver configuration
  • Domain model implementation
  • Score configuration

Travelling Salesman Problem (TSP)

  • Problem statement
  • Problem size
  • Domain model
  • Main method
  • Chaining
  • Solver configuration
  • Domain model implementation
  • Score configuration

Planner configuration

  • Overview
  • Solver configuration
  • Model your planning problem
  • Use the Solver

Score calculation

  • Score terminology
  • Choose a Score definition
  • Calculate the Score
  • Score calculation performance tricks
  • Reusing the Score calculation outside the Solver

Optimization algorithms

  • Search space size in the real world
  • Does Planner find the optimal solution?
  • Architecture overview
  • Optimization algorithms overview
  • Which optimization algorithms should I use?
  • SolverPhase
  • Scope overview
  • Termination
  • SolverEventListener
  • Custom SolverPhase

Move and neighborhood selection

  • Move and neighborhood introduction
  • Generic Move Selectors
  • Combining multiple MoveSelectors
  • EntitySelector
  • ValueSelector
  • General Selector features
  • Custom moves

Construction heuristics

  • First Fit
  • Best Fit
  • Advanced Greedy Fit
  • the Cheapest insertion
  • Regret insertion

Local search

  • Local Search concepts
  • Hill Climbing (Simple Local Search)
  • Tabu Search
  • Simulated Annealing
  • Late Acceptance
  • Step counting hill climbing
  • Late Simulated Annealing (experimental)
  • Using a custom Termination, MoveSelector, EntitySelector, ValueSelector or Acceptor

Evolutionary algorithms

  • Evolutionary Strategies
  • Genetic Algorithms

Hyperheuristics

Exact methods

  • Brute Force
  • Depth-first Search

Benchmarking and tweaking

  • Finding the best Solver configuration
  • Doing a benchmark
  • Benchmark report
  • Summary statistics
  • Statistics per dataset (graph and CSV)
  • Advanced benchmarking

Repeated planning

  • Introduction to repeated planning
  • Backup planning
  • Continuous planning (windowed planning)
  • Real-time planning (event based planning)

Drools

  • Short introduction to Drools
  • Writing Score Function in Drools

Integration

  • Overview
  • Persistent storage
  • SOA and ESB
  • Other environment
 21 時間

参加者の人数



Price per participant

お客様の声 (1)

関連コース

LangChain: Building AI-Powered Applications

14 時間

LangChain Fundamentals

14 時間

H2O AutoML

14 時間

AutoML with Auto-sklearn

14 時間

AutoML with Auto-Keras

14 時間

Advanced Stable Diffusion: Deep Learning for Text-to-Image Generation

21 時間

Introduction to Stable Diffusion for Text-to-Image Generation

21 時間

AlphaFold

7 時間

TensorFlow Lite for Embedded Linux

21 時間

TensorFlow Lite for Android

21 時間

TensorFlow Lite for iOS

21 時間

Tensorflow Lite for Microcontrollers

21 時間

Deep Learning Neural Networks with Chainer

14 時間

Distributed Deep Learning with Horovod

7 時間

Accelerating Deep Learning with FPGA and OpenVINO

35 時間

関連カテゴリー