C2.10 Interactive Evolution

نویسنده

  • Wolfgang Banzhaf
چکیده

We present a diierent approach to directing the evolutionary process through interactive selection of solutions by the human user. First the general context of Interactive Evolution (IE) is set, then the standard IE algorithm is discussed together with more complicated variants. Finally, several application areas are discussed and uses for the new method are exempliied using design from the literature. The basic idea of Interactive Evolution (IE) is to involve a human user on-line into the variation| selection loop of the evolutionary algorithm. This is to be seen in contrast to the conventional participation of the user prior to running the EA by deening a suitable representation of the problem, C1 the tness criterion for evaluation of individual solutions and corresponding operators to improve B2.1 C3 tness quality. In the latter case, the user's role is restricted to passive observation during the EA run. The minimumrequirement for interactive evolution is the deenition of a problem representation, together with a determination of population parameters only. Search operators of arbitrary kind as E1 C3 well as selection according to arbitrary criteria might be applied to the representation by the user. C2 The process is much more comparable to the creation of a piece of art, e.g. a painting, than to the automatic evolution of an optimized problem solution. In IE, the user assumes an active role in the search process. At the minimum level, the IE system must hold present solutions together with variants presently generated or considered. Usually, however, automatic means of variation, i.e. evolutionary search operators using random events, are provided with an IE system. In the present context we shall require the existence of automatic means of variation by operators for mutation and recombination of solutions which are C3.2 C3.3 to be deened prior to running the EA. C2.10.2 History and prospects Dawkins (1986) was the rst to consider an elaborate IE system. The evolution of biomorphs, as he called them, by IE in a system which he had originally intended to be useful for the design of tree-like graphical forms has served as a prototype for many systems developed later on. Starting with the contributions of Sims (1991) and the book of Todd and Latham (1992), computer art developed into the present major application area of IE. F1 Later, interactive evolution of grammar-based structures has been considered (Nguyen et al. 1994 and McCormack 1994). Raw image data have …

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Interactive Evolution in the framework of Simulated Natural Evolution

This paper demonstrates how interactive evolution can be applied to the evolution of simulated natural evolution. Evolutionary algorithmsof selection andvariation by recombination and/ormutation can beused to simulate biological evolution in a computer. Interactive evolution can be used to direct the development of graphicmodels that are simulations of their counterparts in nature. Interactive ...

متن کامل

Potentiometric Studies on Stepwise Mixed Ligand Complex Formation Copper(II)-Iminodiacetic Acid-Hydroxy Acid

Cl6 = 0.3269 Cl7 0.7458 Cl,10 = 0.6322 C26 = 0.6428 C18 0.2978 Ci,11 = — 0.1488 C36 = 0.6725 Cl9 = 0.4364 Cl,12 = — 0.4904 C46 = 0.1488 C27 = 0.1340 C2.10 = 0 Cö6 = 0 C28 = 0.4845 C2.11 = 0 C7.10 = 0.7260 C29 = 0.6087 C2.12 = 0 C7,ll = 0.5467 y s37 = 0.3405 C3.10 = 0.6793 ^7,12 = 0.4507 C38 = 0.0394 C3. l l = 0.6793 £8,10 0.6176 C39 == 0.2440 C3.12 = 0.2151 -8.1 1 = 0.7615 C47 = 0.1087 C4,10 = ...

متن کامل

Leveraging Human Computation Markets for Interactive Evolution

Leveraging human input for selection in an evolutionary algorithm, i.e. interactive evolution, is effective when an appropriate domain fitness function is hard to quantify, but where solution quality is easily recognizable by humans. However, single-user applications of interactive evolution are limited by user fatigue: Humans become bored with monotonous fitness evaluations. This paper shows t...

متن کامل

Hands-free Evolution of 3D-printable Objects via Eye Tracking

Interactive evolution has shown the potential to create amazing and complex forms in both 2-D and 3-D settings. However, the algorithm is slow and users quickly become fatigued. We propose that the use of eye tracking for interactive evolution systems will both reduce user fatigue and improve evolutionary success. We describe a systematic method for testing the hypothesis that eye tracking driv...

متن کامل

Boosting Interactive Evolution Using Human Computation Markets

Interactive evolution, i.e. leveraging human input for selection in an evolutionary algorithm, is effective when an appropriate fitness function is hard to quantify yet solution quality is easily recognizable by humans. However, single-user applications of interactive evolution are limited by user fatigue: Humans become bored with monotonous evaluations. This paper explores the potential for by...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1997