Evolving Modular Neural Networks Which Generalise Well
نویسندگان
چکیده
| In dealing with complex problems, a monolithic neural network often becomes too large and complex to design and manage. The only practical way is to design modular neural network systems consisting of simple modules. While there has been a lot of work on combining diierent modules in a modular system in the elds of neural networks, statistics , and machine learning, little work has been done on how to design those modules automatically and how to exploit the interaction between individual module design and module combination. This paper proposes an evolutionary approach to designing modular neural networks. The approach addresses the issue of automatic determination of the number of individual modules and the exploitation of the interaction between individual module design and module combination. The relationship among diierent modules is considered during the module design. This is quite different from the conventional approach where the module design is separated from the module combination. Experimental results on some benchmark problems are presented and discussed in this paper.
منابع مشابه
معرفی شبکه های عصبی پیمانه ای عمیق با ساختار فضایی-زمانی دوگانه جهت بهبود بازشناسی گفتار پیوسته فارسی
In this article, growable deep modular neural networks for continuous speech recognition are introduced. These networks can be grown to implement the spatio-temporal information of the frame sequences at their input layer as well as their labels at the output layer at the same time. The trained neural network with such double spatio-temporal association structure can learn the phonetic sequence...
متن کاملEvolving 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 کاملEvolving Symmetric and Modular Neural Network Controllers for Multilegged Robots
Controllers for multilegged robots are characterized by modularity and symmetry. However, the controller symmetries necessary for generating appropriate gaits are often difficult to determine analytically. This paper utilizes a nature-inspired approach called Evolution of Network Symmetry and mOdularity (ENSO) to evolve such controllers automatically. It uses group theory to mutate symmetry sys...
متن کاملUsing Neural Networks for Strategy Selection in Real-Time Strategy Games
Video games continue to grow in importance as a platform for Artificial Intelligence (AI) research since they offer a rich virtual environment without the noise present in the real world. In this paper, a simulated ship combat game is used as an environment for evolving neural network controlled ship combat strategies. Domain knowledge is used as input to the Artificial Neural Networks (ANNs) t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1997