#### Filter Results:

#### Publication Year

1990

2007

#### Publication Type

#### Co-author

#### Publication Venue

#### Key Phrases

Learn More

- F J Smieja
- 1991

There are currently several types of constructive, or growth, algorithms available for training a feed-forward neural network. This paper describes and explains the main ones, using a fundamental approach to the multi-layer perceptron problem-solving mechanisms. The claimed convergence properties of the algorithms are veriied using just two mapping theorems… (More)

- Uwe Beyer, Frank Smieja
- 1993

Learning from examples has a number of distinct algebraic forms, depending on what is to be learned from which available information. One of these forms is x G ! y, where the input{output tuple (x; y) is the available information , and G represents the process determining the mapping from x to y. Various models , y = f(x), of G can be constructed using the… (More)

The Pandemonium system of reflective MINOS agents solves problems by automatic dynamic modularization of the input space. The agents contain feedforward neural networks which adapt using the backpropagation algorithm. We demonstrate the performance of Pandemonium on various categories of problems. These include learning continuous functions with… (More)

- Uwe Beyer, Frank Smieja
- 1996

Adaptive models of systems seek to emulate the processes giving rise to the data observed in the system. The process is often termed learning from examples, or data-driven information processing. An important issue regarding such modeling is the active selection of data by the modeling process, or exploration. If exploration depends on the current state of… (More)

- Uwe Beyer, Frank Smieja
- 1994

In this report we describe the JANUS robot project in terms of the maxims followed at the various levels of construction. The project involves designing a two-armed robot which operates in an open system. To make this possible it must have exibility and heterogeneity in its architecture. The key ingredients of JANUS are presented in the form of seven… (More)

Learning from examples has a number of distinct algebraic forms, depending on what is to be learned from which available information. One of these forms is x G ! y, where the input{output tuple (x; y) is the available information, and G represents the process determining the mapping from x to y. Various models, y = f(x), of G can be constructed using the… (More)

- Uwe Beyer, Frank Smieja
- 1997

Inversion of the kinematics of ma-nipulators is one of the central problems in the eld of robot arm control. The iterative use of inverse diierential kinematics is a popular method of solving this task. Normally the solution of the problem requires a complex mathematical apparatus. It involves methods for solving equation systems as well as algorithms for… (More)

An extended feed-forward algorithm for recurrent connectionist networks is presented. This algorithm, which works locally in time, is derived both for discrete-in-time networks and for continuous networks. Several standard gradient descent algorithms for connectionist networks (e.g. 48], 30], 28] 15], 34]), especially the backpropagation algorithm 36], are… (More)

- Frank Smieja
- 1996

The Pandemonium system of reeec-tive MINOS agents solves problems by automatic dynamic modularization of the input space. The agents contain feed-forward neural networks which adapt using the back-propagation algorithm. We demonstrate the performance of Pandemonium on various categories of problems. These include learning continuous functions with… (More)

- F J Smieja, H M Uhlenbein
- 1992

Many of the current artiicial neural network systems have serious limitations, concerning accessibility , exibility, scaling and reliability. In order to go some way to removing these we suggest a reeective neural network architecture. In such an architecture, the modular structure is the most important element. The building-block elements are called… (More)