A Representation for the Adaptive Generation of Simple Sequential Programs

By N. Cramer. 1985

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Learning to Optimize Neural Nets (2017, methodology): “Various approaches have been explored: Cramer (1985) investigated evolving programs represented as abstract syntax trees using genetic algorithms, Liang et al. (2010) deﬁnes a hierarchical Bayesian prior over programs in a formal language and infers the best program using approximate sampling and…”
Deep learning in neural networks: An overview (2014, background): “Compare Genetic Programming (GP) (Cramer, 1985) (see also Smith, 1980)which can be used to evolve computer programs of variable size (Dickmanns, Schmidhuber, & Winklhofer, 1987; Koza, 1992), and Cartesian GP (Miller &Harding, 2009; Miller & Thomson, 2000) for evolving graph-like programs, including…”
Learning programs from noisy data (2016, background): “The following work [8] discusses the language design decisions to encode a program synthesis problem from input/output examples into genetic programming.”
Gene Expression Programming in Problem Solving (2002, unknown): “double APSCfunction(double d[ ]) { double dblTemp = 0; dblTemp+=sin(sin(((log10(cos(d[1]))-d[2])*tan(d[0])))); dblTemp += d[0]; dblTemp += tan((d[3]-d[4])); return dblTemp; }”
Automatic programming: The open issue? (2019, background): “…representation has long been a subject of research in genetic programming, with work exploring genetic encodings such as binary, integer, tree, linear-tree, graphs, and grammars (e.g., [7, 8, 10–13, 27, 32, 42, 43, 67]), along with work on searching the representation space itself [29, 47, 59].”
A comparison of linear genetic programming and neural networks in medical data mining (2001, background): “The use of linear bit sequences in GP again goes back to Cramer and his JB language [7].”
Evolutionary computation: a unified approach (2018, background): “The good news is that there are a few programming languages that seem reasonably wellsuited for EA-based techniques: low level machine languages (Cramer, 1985; Ray, 1994), Lisp (Fujiki and Dickinson, 1987; Koza, 1992), and rule-based languages (Holland, 1975; Smith, 1983; Grefenstette, 1989).”
Assessment of artificial neural network and genetic programming as predictive tools (2015, methodology): “Cramer [13] applied genetic algorithms (GAs) to evolve programs and introduced tree-like GP structures.”
Gödel Machines: Fully Self-referential Optimal Universal Self-improvers (2007, background): “Similar drawbacks hold for Lenat’s human-assisted, nonautonomous, self-modifying learner [22], our Meta-Genetic Programming [32] extending Cramer’s Genetic Programming [8, 1], our metalearning economies [32] extending Holland’s machine learning economies [15], and gradient-based metalearners for con”
Simple Principles of Metalearning (1996, background): “…programs and time-limits (unlike, e.g., \Genetic Programming"(GP)),LS may also be of interest for researchersworking in GP and related (cid:12)elds | among the (cid:12)rst papers on using GP-like algorithms to evolve assembler-like computer programs are (Cramer, 1985; Dickmanns et al., 1987).”
Metaheuristics (2016, methodology): “This general principle of crossover, introduced by Cramer in 1985 [15] can be refined with different extensions to constrain the size of the generated offspring.”
Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes (2008, background): “, [36, 75, 15, 46]) are necessary to extract the underlying algorithmic regularity.”
Evolving virtual creatures (1994, methodology): “This approach has been used to genetically program solutions to a variety of problems [1,9], as well as to explore procedurally generated images and dynamical systems [18,19].”