#### Filter Results:

#### Publication Year

1993

2004

#### Publication Type

#### Co-author

#### Key Phrase

#### Publication Venue

Learn More

Recurrent neural networks possess interesting universal approximation capabilities, making them good candidates for time-series modeling. Unfortunately, long-term dependencies are diicult to learn if gradient descent algorithms are employed. We support the view that it is easier for these algorithms to ÿnd good solutions if time-delayed connections are… (More)

Recurrent neural networks possess interesting universal approximation capabilities, making them good candidates for time series modeling. Unfortunately, long term dependencies are difficult to learn if gradient descent algorithms are employed. We support the view that it is easier for these algorithms to find good solutions if one includes connections with… (More)

sets of neural networks and we use the mean predictions. Also, we develop models on different training sets and test them on different tests sets before concluding that one class of models is superior to the others. We study the problem of generating monthly forecasts of the CAC 40 financial index. We compare the results obtained by linear models and… (More)

YANNS (Yet Another Neural Network Simulator) is a new object-oriented neural network simulator for feedforward networks as well as general recurrent networks. The goal of this project is to develop and implement a simulation tool that satisfies the following constraints: flexibility, ease of use, portability and efficiency. The result is a simulator with… (More)

We extend the Bayesian framework to Multi-Layer Perceptron models of Non-linear Auto-Regressive time-series. The approach is evaluated on an artificial time-series and some common simplifications are discussed.