Feed-forward Network Algorithm Research Articles

Modeling Liquid Thermal Conductivity of Low-GWP Refrigerants Using Neural Networks

The thermal conductivity of refrigerants is needed to optimize and design the main components of HVAC&R systems. Consequently, it is crucial to have reliable models that are able to accurately calculate the temperature and pressure dependence of the thermal conductivity of refrigerants. For the first time, this study presents a neural network specifically developed to calculate the liquid thermal conductivity of various low-GWP-based refrigerants. In detail, a feed-forward network algorithm with 5 input parameters (i.e., the reduced temperature, the critical pressure, the acentric factor, the molecular weight, and the reduced pressure) and 1 hidden layer was applied to a large dataset of 3404 experimental points for 7 halogenated alkene refrigerants. The results provided by the neural network algorithm were very satisfactory, achieving an absolute average relative deviation of 0.389% with a maximum absolute relative deviation of 6.074% over the entire dataset. In addition, the neural network ensured lower deviations between the experimental and calculated data than that produced using different literature models, proving its accuracy for the liquid thermal conductivity of the studied refrigerants.

Properties of a Batch Training Algorithm for Feedforward Networks

We examine properties for a batch training algorithm known as the output weight optimization---hidden weight optimization (OWO---HWO). Using the concept of equivalent networks, we analyze the effect of input transformation on BP. We introduce new theory of affine invariance and partial affine invariance for neural networks and prove this property for OWO---HWO. Finally, we relate HWO to BP and show that every iteration of HWO is equivalent to BP applied to whitening transformed data. Experimental results validate the connection between OWO---HWO and OWO---BP.

IDENTIFYING OPTIMAL NUMBER OF ORTHONORMALISATION IN LEARNING ALGORITHM USING WEATHER FORECASTING

Artificial neural networks are more powerful than any other traditional expert system in the classification of patterns, which are non linear and in performing pattern classification tasks because they learn from examples without explicitly stating the rules. Multilayered feed forward neural networks possess a number of properties, which make them particularly suited to complex problems. Their applications to some real world problems are hampered by the lack of a training algorithm which finds a globally optimal set of weights in a relatively short time. Genetic algorithms are a class of optimization procedures, which are good at exploring a large and complex space in an intelligent way to find values close to the global optimum. In this study, conversion of random weights into orthonormal weights (orthonormalisation) in feed forward network algorithm is proposed and also optimal number of orthonormalisation of weight is evaluated. Orthonormal weight based artificial neural network algorithms not only succeed in its task but also outperforms the genetic algorithm. This success comes from orthonormal weights instead of random and genetic weights. This paper has documented the evolution and ultimate success of this algorithm using weather forecasting data.

Learning algorithms for feedforward networks based on finite samples

We present two classes of convergent algorithms for learning continuous functions and regressions that are approximated by feedforward networks. The first class of algorithms, applicable to networks with unknown weights located only in the output layer, is obtained by utilizing the potential function methods of Aizerman et al. (1970). The second class, applicable to general feedforward networks, is obtained by utilizing the classical Robbins-Monro style stochastic approximation methods (1951). Conditions relating the sample sizes to the error bounds are derived for both classes of algorithms using martingale-type inequalities. For concreteness, the discussion is presented in terms of neural networks, but the results are applicable to general feedforward networks, in particular to wavelet networks. The algorithms can be directly adapted to concept learning problems.

An efficient constrained training algorithm for feedforward networks

A novel algorithm is presented which supplements the training phase in feedforward networks with various forms of information about desired learning properties. This information is represented by conditions which must be satisfied in addition to the demand for minimization of the usual mean square error cost function. The purpose of these conditions is to improve convergence, learning speed, and generalization properties through prompt activation of the hidden units, optimal alignment of successive weight vector offsets, elimination of excessive hidden nodes, and regulation of the magnitude of search steps in the weight space. The algorithm is applied to several small- and large-scale binary benchmark training tasks, to test its convergence ability and learning speed, as well as to a large-scale OCR problem, to test its generalization capability. Its performance in terms of percentage of local minima, learning speed, and generalization ability is evaluated and found superior to the performance of the backpropagation algorithm and variants thereof taking especially into account the statistical significance of the results.

Modified extended Kalman filtering for supervised learning

Abstract We apply the modified extended Kalman filter to develop a learning algorithm for feedforward networks. The resulting algorithm improves the existing extended Kalman filter based scheme in both speed of convergence and accuracy of estimation.

In search of an optimal dilution algorithm for feedforward networks

In a recent paper the authors presented a dilution algorithm that yields a storage capacity per synapse alpha eff larger than 2. In this letter, two new algorithms with even higher alpha eff values are introduced. They study a one-step dilution algorithm, where the perceptron is used to select a fraction of the couplings to be removed. For the remaining bonds the perceptron of optimal stability is relearned. They further compare simulation data from an iterative version of the one-step dilution algorithm with phase-space volume calculations.