Gene Expression Programming (GEP) is introduced as a new technique for creating computer programs, utilizing a genotype/phenotype genetic algorithm. GEP uses linear chromosomes composed of genes structured in a head and a tail, which function as genomes and are modified through various genetic operators such as mutation, transposition, and recombination. These chromosomes encode expression trees (ETs), which are the objects of selection. The separation of the genome and ETs allows GEP to perform efficiently, surpassing existing adaptive techniques. The paper discusses the structural and functional organization of GEP chromosomes, the translation of chromosomes into ETs, and the interaction of sub-ETs to form more complex structures. GEP is applied to various problems, including symbolic regression, sequence induction, block stacking, cellular automata rules, and boolean concept learning, demonstrating its versatility and effectiveness. The fitness functions and selection methods are also described, along with the detailed implementation of genetic operators. The results show that GEP can efficiently evolve solutions, especially for complex problems, and is superior to other evolutionary techniques in terms of performance and adaptability.Gene Expression Programming (GEP) is introduced as a new technique for creating computer programs, utilizing a genotype/phenotype genetic algorithm. GEP uses linear chromosomes composed of genes structured in a head and a tail, which function as genomes and are modified through various genetic operators such as mutation, transposition, and recombination. These chromosomes encode expression trees (ETs), which are the objects of selection. The separation of the genome and ETs allows GEP to perform efficiently, surpassing existing adaptive techniques. The paper discusses the structural and functional organization of GEP chromosomes, the translation of chromosomes into ETs, and the interaction of sub-ETs to form more complex structures. GEP is applied to various problems, including symbolic regression, sequence induction, block stacking, cellular automata rules, and boolean concept learning, demonstrating its versatility and effectiveness. The fitness functions and selection methods are also described, along with the detailed implementation of genetic operators. The results show that GEP can efficiently evolve solutions, especially for complex problems, and is superior to other evolutionary techniques in terms of performance and adaptability.