Abstract
A variety of neural models, especially higher-order networks, are known to be computationally powerful for complex applications. While they have advantages over traditional multilayer perceptrons, the non-uniformity in their network structures and learning algorithms creates practical problems. Thus there is a need for a framework that unifies these various models. This paper presents a novel neuron model, called generalized multi-dendrite product (GMDP) unit. Multi-layer feedforward neural networks with GMDP units are shown to be capable of realizing higher-order neural networks. The standard backpropagation learning rule is extended to this neural network. Simulation results show that single layer GMDP networks provide an efficient model for solving general problems on function approximation and pattern classification.
Original language | English |
---|---|
Pages | 107-112 |
Number of pages | 6 |
Publication status | Published - 1994 Dec 1 |
Event | Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA Duration: 1994 Jun 27 → 1994 Jun 29 |
Other
Other | Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) |
---|---|
City | Orlando, FL, USA |
Period | 94-06-27 → 94-06-29 |
All Science Journal Classification (ASJC) codes
- Software