Robert T. Pennock

Publications90
h-index21
Citations2,266
Highly Influential Citations98
Claim Author Page
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • C. Ofria
  • 192 Publications • 6,500 Citations
  • J. Clune
  • 118 Publications • 17,902 Citations
  • Kenneth O. Stanley
  • 221 Publications • 16,700 Citations
  • R. Lenski
  • 360 Publications • 38,053 Citations
  • Publications
  • Influence
The evolutionary origin of complex features
TLDR
Findings show how complex functions can originate by random mutation and natural selection.
On the Performance of Indirect Encoding Across the Continuum of Regularity
TLDR
This paper presents the first comprehensive study showing that phenotypic regularity enables an indirect encoding to outperform direct encoding controls as problem regularity increases, and suggests a path forward that combines indirect encodings with a separate process of refinement.
Evolving coordinated quadruped gaits with the HyperNEAT generative encoding
TLDR
It is demonstrated that HyperNEAT, a new and promising generative encoding for evolving neural networks, can evolve quadruped gaits without an engineer manually decomposing the problem.
Tower of Babel: The Evidence against the New Creationism
Creationism is no longer the simple notion it once was taken to be. Its new advocates have become more sophisticated in how they present their views, speaking of "intelligent design" rather than…
The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities
Evolution provides a creative fount of complex and subtle adaptations that often surprise the scientists who discover them. However, the creativity of evolution is not limited to the natural world:…
The sensitivity of HyperNEAT to different geometric representations of a problem
TLDR
The results suggest that HyperNEAT practitioners can obtain good results even if they do not know how to geometrically represent a problem, and that further improvements are possible with a well-chosen geometric representation.
LEARNING EVOLUTION AND THE NATURE OF SCIENCE USING EVOLUTIONARY COMPUTING AND ARTIFICIAL LIFE
TLDR
A new A-Life software environment - Avida-ED - is described in which undergraduate students can test evolutionary hypotheses directly using digital organisms that evolve on their own through the very mechanisms that Darwin discovered.
Creationism and intelligent design.
TLDR
Creationism, the rejection of evolution in favor of supernatural design, comes in many varieties besides the common young-earth Genesis version, and scientists need to be ready to defend good evolution education.
Developing a Scientific Virtue-Based Approach to Science Ethics Training
TLDR
This paper motivates and describes three implementations of a new approach to science ethics training based upon Pennock’s notion of the scientific virtues that have been developed in courses and workshops to introduce students to this scientific virtue-based approach.
HybrID: A Hybridization of Indirect and Direct Encodings for Evolutionary Computation
TLDR
A new algorithm is proposed, a Hybridized Indirect and Direct encoding (HybrID), which discovers the regularity of a problem with an indirect encoding and accounts for irregularities via a direct encoding, suggesting that hybridizing indirect and direct encodings can be an effective way to improve the performance of evolutionary algorithms.
...
1
2
3
4
5
...