Evolution of Low Complexity Arti cial Neural
نویسندگان
چکیده
siGis-002-1996 May 24, 1996 Evolution of Low Complexity Arti cial Neural Networks for Land Cover Classi cation from Remote Sensing Data 20th Workshop of the Austrian Pattern Recognition Group ( OAGM) May 9{10, 1996, Schlo Seggau, Leibnitz, Austria Roland Schwaiger Helmut A. Mayer Reinhold Huber [email protected] [email protected] [email protected] Department of Computer Science University of Salzburg
منابع مشابه
Evolving Neural Networks for Chlorophyll a Prediction
This paper studies the application of evolutionary arti cial neural networks to chlorophyll a pre diction in Lake Kasumigaura Unlike previous applications of arti cial neural networks in this eld the architecture of the arti cial neural network is evolved automatically rather than designed man ually The evolutionary system is able to nd a near optimal architecture of the arti cial neural networ...
متن کاملEvolutionary Arti cial Neural Networks 12 Xin
Evolutionary arti cial neural networks (EANNs) [1] result from combinations of arti cial neural networks (ANNs) and evolutionary search procedures such as genetic algorithms (GAs). This article introduces the concept of EANNs, reviews the current state-of-the-art and indicates possible future research directions. X. Yao: Evolutionary Arti cial Neural Networks 1
متن کاملEvolving Neural Network Structures Using Axonal Growth Mechanisms
In the eld of arti cial evolution creating methods to evolve neural networks is an important goal. But how to encode the structure and properties of the neural network in the genome is still a problem. If one overloads the genome with detailed information for a network the evolutionary time increases prohibitively. If the genome is too simple, only simple problems can be solved. As Nature has f...
متن کاملLamarckian training of feedforward neural networks
Living creatures improve their adaptation capabilities to a changing world by means of two orthogonal processes: evolution and lifetime learning. Within Arti cial Intelligence, both mechanisms inspired the development of non-orthodox problem solving tools, namely Genetic and Evolutionary Algorithms (GEAs) and Arti cial Neural Networks (ANNs). Several local search gradient-based methods have bee...
متن کاملDimensions of Neural-symbolic Integration - A Structured Survey
Research on integrated neural-symbolic systems has made signi cant progress in the recent past. In particular the understanding of ways to deal with symbolic knowledge within connectionist systems (also called arti cial neural networks) has reached a critical mass which enables the community to strive for applicable implementations and use cases. Recent work has covered a great variety of logic...
متن کامل