Genetic Programming IV: Routine Human-Competitive Machine Intelligence (Genetic Programming)

__Genetic Programming IV:__ **Routine Human-Competitive Machine Intelligence** presents the application of GP to a wide variety of problems involving automated synthesis of controllers, circuits, antennas, genetic networks, and metabolic pathways. The book describes fifteen instances where GP has created an entity that either infringes or duplicates the functionality of a previously patented 20th-century invention, six instances where it has done the same with respect to post-2000 patented inventions, two instances where GP has created a patentable new invention, and thirteen other human-competitive results. The book additionally establishes: GP now delivers routine human-competitive machine intelligence GP is an automated invention machine GP can create general solutions to problems in the form of parameterized topologies GP has delivered qualitatively more substantial results in synchrony with the relentless iteration of Moore's Law Introduction....Pages 1-28 Background on Genetic Programming....Pages 29-48 Automatic Synthesis of Controllers....Pages 49-127 Automatic Synthesis of Circuits....Pages 129-174 Automatic Synthesis of Circuit Topology, Sizing, Placement, and Routing....Pages 175-203 Automatic Synthesis of Antennas....Pages 205-220 Automatic Synthesis of Genetic Networks....Pages 221-227 Automatic Synthesis of Metabolic Pathways....Pages 229-280 Automatic Synthesis of Parameterized Topologies for Controllers....Pages 281-300 Automatic Synthesis of Parameterized Topologies for Circuits....Pages 301-339 Automatic Synthesis of Parameterized Topologies with Conditional Developmental Operators for Circuits....Pages 341-366 Automatic Synthesis of Improved Tuning Rules for PID Controllers....Pages 367-385 Automatic Synthesis of Parameterized Topologies for Improved Controllers....Pages 387-412 Reinvention of Negative Feedback....Pages 413-419 Automated Reinvention of Six Post-2000 Patented Circuits....Pages 421-482 Problems for Which Genetic Programming May Be Well Suited....Pages 483-514 Parallel Implementation and Computer Time....Pages 515-522 Historical Perspective on Moore’s Law and the Progression of Qualitatively More Substantial Results Produced by Genetic Programming....Pages 523-527 Conclusion....Pages 529-532

Genetic Programming IV: Routine Human-Competitive Machine Intelligence presents the application of GP to a wide variety of problems involving automated synthesis of controllers, circuits, antennas, genetic networks, and metabolic pathways. The book describes fifteen instances where GP has created an entity that either infringes or duplicates the functionality of a previously patented 20th-century invention, six instances where it has done the same with respect to post-2000 patented inventions, two instances where GP has created a patentable new invention, and thirteen other human-competitive results. The book additionally establishes:

GP now delivers routine human-competitive machine intelligence

GP is an automated invention machine

GP can create general solutions to problems in the form of parameterized topologies

GP has delivered qualitatively more substantial results in synchrony with the relentless iteration of Moore's Law

The goal of getting computers to automatically solve problems is central to artificial intelligence, machine learning, and the broad area encompassed by what Turing called "machine intelligence" (Turing 1948, 1950).