谈判 发表于 2025-3-30 08:24:39
Book 1999ective is to predict the future value of some entity of interest on the basis of a time series of past measurements or observations. Typical training schemes aim to minimise the sum of squared deviations between predicted and actual values (the ‘targets‘), by which, ideally, the network learns the c烧瓶 发表于 2025-3-30 15:12:38
A Universal Approximator Network for Predicting Conditional Probability Densities, networks are presented, and their relation to a stochastic kernel expansion is noted. The chapter concludes with a comparison between these models and several relevant alternative approaches which have recently been introduced to the neural network community.ALB 发表于 2025-3-30 16:49:06
A Maximum Likelihood Training Scheme,s shown to suffer from considerable inherent convergence problems due to large curvature variations of the error surface. A simple rectification scheme based on a curvature-based shape modification of E is presented.我要沮丧 发表于 2025-3-30 23:28:37
Demonstration: Committees of Networks Trained with Different Regularisation Schemes,heme is found to lead to superior results. However, when using network committees, under-regularisation can be advantageous, since it leads to a larger model diversity, as a result of which a more substantial decrease of the generalisation ‘error’ can be achieved.愤慨点吧 发表于 2025-3-31 04:55:16
http://reply.papertrans.cn/67/6638/663714/663714_55.pngdebris 发表于 2025-3-31 07:04:27
Introduction, weather, or the economy, it is not possible to solve the equations of dynamics explicitly and to keep track of motion in the high dimensional state space. In these cases model-based forecasting becomes impossible and calls for a different prediction paradigm.EXTOL 发表于 2025-3-31 12:49:53
Benchmark Problems,l potential subject to Brownian dynamics. The resulting time series shows fast oscillation around one of two metastable states and occasional phase transitions between these two states. As a consequence of the latter, long-term predictions require a model that can capture bimodality.inventory 发表于 2025-3-31 15:07:47
http://reply.papertrans.cn/67/6638/663714/663714_58.pngAnthrp 发表于 2025-3-31 20:19:53
http://reply.papertrans.cn/67/6638/663714/663714_59.pngEtching 发表于 2025-4-1 01:38:12
Summary,sons discussed in Chapter 1, the distribution is likely to be distorted and may be multimodal. This suggests that, in general, it is not sufficient to train a network to predict only a single value, but that the complete probability distribution of the target conditional on the input vector should be modelled.