Displaying similar documents to “On the behaviour of learning algorithms in a changing environment with application to data network routing problem”

Comparison of supervised learning methods for spike time coding in spiking neural networks

Andrzej Kasiński, Filip Ponulak (2006)

International Journal of Applied Mathematics and Computer Science

Similarity:

In this review we focus our attention on supervised learning methods for spike time coding in Spiking Neural Networks (SNNs). This study is motivated by recent experimental results regarding information coding in biological neural systems, which suggest that precise timing of individual spikes may be essential for efficient computation in the brain. We are concerned with the fundamental question: What paradigms of neural temporal coding can be implemented with the recent learning methods?...

Epoch-incremental reinforcement learning algorithms

Roman Zajdel (2013)

International Journal of Applied Mathematics and Computer Science

Similarity:

In this article, a new class of the epoch-incremental reinforcement learning algorithm is proposed. In the incremental mode, the fundamental TD(0) or TD(λ) algorithm is performed and an environment model is created. In the epoch mode, on the basis of the environment model, the distances of past-active states to the terminal state are computed. These distances and the reinforcement terminal state signal are used to improve the agent policy.

New challenges in dynamical systems: The networked case

Peter H. Bauer (2008)

International Journal of Applied Mathematics and Computer Science

Similarity:

This paper describes new technical challenges that arise from networking dynamical systems. In particular, the paper takes a look at the underlying phenomena and the resulting modeling problems that arise in such systems. Special emphasis is placed on the problem of synchronization, since this problem has not received as much attention in the literature as the phenomena of packet drop, delays, etc. The paper then discusses challenges arising in prominent areas such as congestion control,...

An effective way to generate neural network structures for function approximation.

Andreas Bastian (1994)

Mathware and Soft Computing

Similarity:

One still open question in the area of research of multi-layer feedforward neural networks is concerning the number of neurons in its hidden layer(s). Especially in real life applications, this problem is often solved by heuristic methods. In this work an effective way to dynamically determine the number of hidden units in a three-layer feedforward neural network for function approximation is proposed.