#### Filter Results:

#### Publication Year

1990

2003

#### Publication Type

#### Co-author

#### Publication Venue

Learn More

- Alois P Heinz
- 1994

We introduce the adaptive fuzzy logic network (AFLN) as the appropriate architecture for the realization of fuzzy membership and fuzzy logic functions. The according AFLN to a given training set is easily constructed and optimized. As their main advantage AFLNs provide for a very eecient sequential implementation of fuzzy systems. This eeciency is achieved… (More)

- Alois P Heinz
- 1995

We propose a new parallel implementation of the neural tree feed-forward network architecture that supports eecient evaluation and learning regardless of the number of layers. The neurons of each layer operate in parallel and the layers are the elements of a pipeline that computes the output evaluation vectors for a sequence of input pattern vectors at a… (More)

- Alois P Heinz
- 1994

| We propose the lazy neural tree (LNT) as the appropriate architecture for the realization of smooth regression systems. The LNT is a hybrid of a decision tree and a neural network. From the neural network it inherits smoothness of the generated function , incremental adaptability, and conceptual simplicity. From the decision tree it inherits the topology… (More)

- Alois P Heinz
- 1994

- Alois P Heinz
- 1996

| A tree-structured neural network (TSNN) is described that meets the special requirements of real-time adaptive modeling and control. It is shown that TSNN are capable of arbitrarily accurate approximation to a given function and its derivatives under certain conditions. The evaluation of a TSNN function and its Jacobian is extremely eecient due to the… (More)

- Alois P Heinz
- 1995

We propose Adaptive Fuzzy Neural Trees as an appropriate tool for intelligent data analysis, comprehension , and prediction. Instead of using a single technique Adaptive Fuzzy Neural Trees as a mixture of paradigms combine the main advantages of neural networks, decision trees, and fuzzy logic. Like neural networks they are able to model smooth functions… (More)

- Alois P Heinz
- 1998

Tree-structured neural networks (TSNN) are known to be universal ap-proximators that have easily derivable equivalent implementations as feed-forward neural networks with two hidden layers. What makes them particularly interesting for large-scale and real-time applications such as adaptive control is their ability to support eecient lazy evaluation by… (More)

- Alois P Heinz
- 1995

We propose a new class of artiicial neural networks for regression tasks and its construction algorithm. These networks have two diierent but isomorphic layouts. The tree-structured layout is used and built up during the construction phase and it can be used for accelerated serial evaluation of the network. The three-layer layout can be derived from the… (More)