Feedforward neural network

About: Feedforward neural network is a research topic. Over the lifetime, 11431 publications have been published within this topic receiving 310905 citations. The topic is also known as: feed-forward neural network & feed forward neural network.

Gauss-Newton approximation to Bayesian learning

Abstract: This paper describes the application of Bayesian regularization to the training of feedforward neural networks. A Gauss-Newton approximation to the Hessian matrix, which can be conveniently implemented within the framework of the Levenberg-Marquardt algorithm, is used to reduce the computational overhead. The resulting algorithm is demonstrated on a simple test problem and is then applied to three practical problems. The results demonstrate that the algorithm produces networks which have excellent generalization capabilities.

Progress in supervised neural networks

Abstract: Theoretical results concerning the capabilities and limitations of various neural network models are summarized, and some of their extensions are discussed. The network models considered are divided into two basic categories: static networks and dynamic networks. Unlike static networks, dynamic networks have memory. They fall into three groups: networks with feedforward dynamics, networks with output feedback, and networks with state feedback, which are emphasized in this work. Most of the networks discussed are trained using supervised learning. >

First- and second-order methods for learning: between steepest descent and Newton's method

Abstract: On-line first-order backpropagation is sufficiently fast and effective for many large-scale classification problems but for very high precision mappings, batch processing may be the method of choice. This paper reviews first- and second-order optimization methods for learning in feedforward neural networks. The viewpoint is that of optimization: many methods can be cast in the language of optimization techniques, allowing the transfer to neural nets of detailed results about computational complexity and safety procedures to ensure convergence and to avoid numerical problems. The review is not intended to deliver detailed prescriptions for the most appropriate methods in specific applications, but to illustrate the main characteristics of the different methods and their mutual relations.

Recurrent neural networks and robust time series prediction

Abstract: We propose a robust learning algorithm and apply it to recurrent neural networks. This algorithm is based on filtering outliers from the data and then estimating parameters from the filtered data. The filtering removes outliers from both the target function and the inputs of the neural network. The filtering is soft in that some outliers are neither completely rejected nor accepted. To show the need for robust recurrent networks, we compare the predictive ability of least squares estimated recurrent networks on synthetic data and on the Puget Power Electric Demand time series. These investigations result in a class of recurrent neural networks, NARMA(p,q), which show advantages over feedforward neural networks for time series with a moving average component. Conventional least squares methods of fitting NARMA(p,q) neural network models are shown to suffer a lack of robustness towards outliers. This sensitivity to outliers is demonstrated on both the synthetic and real data sets. Filtering the Puget Power Electric Demand time series is shown to automatically remove the outliers due to holidays. Neural networks trained on filtered data are then shown to give better predictions than neural networks trained on unfiltered time series. >

Extreme Learning Machine for Multilayer Perceptron

Abstract: Extreme learning machine (ELM) is an emerging learning algorithm for the generalized single hidden layer feedforward neural networks, of which the hidden node parameters are randomly generated and the output weights are analytically computed. However, due to its shallow architecture, feature learning using ELM may not be effective for natural signals (e.g., images/videos), even with a large number of hidden nodes. To address this issue, in this paper, a new ELM-based hierarchical learning framework is proposed for multilayer perceptron. The proposed architecture is divided into two main components: 1) self-taught feature extraction followed by supervised feature classification and 2) they are bridged by random initialized hidden weights. The novelties of this paper are as follows: 1) unsupervised multilayer encoding is conducted for feature extraction, and an ELM-based sparse autoencoder is developed via $\ell _{1}$ constraint. By doing so, it achieves more compact and meaningful feature representations than the original ELM; 2) by exploiting the advantages of ELM random feature mapping, the hierarchically encoded outputs are randomly projected before final decision making, which leads to a better generalization with faster learning speed; and 3) unlike the greedy layerwise training of deep learning (DL), the hidden layers of the proposed framework are trained in a forward manner. Once the previous layer is established, the weights of the current layer are fixed without fine-tuning. Therefore, it has much better learning efficiency than the DL. Extensive experiments on various widely used classification data sets show that the proposed algorithm achieves better and faster convergence than the existing state-of-the-art hierarchical learning methods. Furthermore, multiple applications in computer vision further confirm the generality and capability of the proposed learning scheme.