The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We propose a multiclass hierarchical abductive learning classifier and apply it to improve the recognition rate of handwritten numerals while reduce the dimensionality of the feature space. For handwritten recognition, there are ten classes. Using 9 binary GMDH-based neural network models structured in a hierarchy has led to improving balance factor of the dataset for each classifier and improving...
In a probability learning task, participants estimate the probabilistic reward contingencies, and this task has been used extensively to study instrumental conditioning with partial reinforcement. In the probabilistic reversal learning task, the probabilistic reward contingencies are reversed between options in the middle of the experiment to measure how well people adapt to new contingency situations...
The maze traversal problem involves finding the shortest distance to the goal from any position in a maze. Such maze solving problems have been an interesting challenge in computational intelligence. Previous work has shown that grid-to-grid neural networks such as the cellular simultaneous recurrent neural network (CSRN) can effectively solve simple maze traversing problems better than other iterative...
This paper discusses the effectiveness of deep auto-encoder neural networks in visual reinforcement learning (RL) tasks. We propose a framework for combining the training of deep auto-encoders (for learning compact feature spaces) with recently-proposed batch-mode RL algorithms (for learning policies). An emphasis is put on the data-efficiency of this combination and on studying the properties of...
Artificial Neural Networks have previously been applied in neuro-symbolic learning to learn ground logic program rules. However, there are few results of learning relations using neuro-symbolic learning. This paper presents the system PAN, which can learn relations. The inputs to PAN are one or more atoms, representing the conditions of a logic rule, and the output is the conclusion of the rule. The...
This paper presents a method to improve generalization capabilities of supervised neural networks based on topological data mapping used in Counter Propagation Networks (CPNs). Using topological data mapping on CPNs the method presented herein provides advantages to interpolate new data in sparse areas that exist among categories and to remove overlapping or conflicting data in original training data...
When training a neural network it is tempting to experiment with architectures until a low total error is achieved. The danger in doing so is the creation of a network that loses generality by over-learning the training data; lower total error does not necessarily translate into a low total error in validation. The resulting network may keenly detect the samples used to train it, without being able...
Data normalization is a fundamental preprocessing step for mining and learning from data. However, finding an appropriated method to deal with time series normalization is not a simple task. This is because most of the traditional normalization methods make assumptions that do not hold for most time series. The first assumption is that all time series are stationary, i.e., their statistical properties,...
It is well-known that ensemble performance relies heavily on sufficient diversity among the base classifiers. With this in mind, the strategy used to balance diversity and base classifier accuracy must be considered a key component of any ensemble algorithm. This study evaluates the predictive performance of neural network ensembles, specifically comparing straightforward techniques to more sophisticated...
The present paper is investigating the modelling of the McGurk effect, an audio-visual speech perceptual illusion, with a distributed model of memory. The network is trained with congruent auditory and visual patterns and tested with incongruent sets of patterns considered to produce the McGurk effect.
In neural networks, when new patterns are learned by a network, the new information radically interferes with previously stored patterns. This drawback is called catastrophic forgetting or catastrophic interference. In this paper, we propose a biologically inspired neural network model which overcomes this problem. The proposed model consists of two distinct networks: one is a Hopfield type of chaotic...
A neural network method is adopted to predict the football game's winning rate of two teams according to their previous stage's official statistical data of 2006 World Cup Football Game. The adopted prediction model is based on multi-layer perceptron (MLP) with back propagation learning rule. The input data are transformed to the relative ratios between two teams of each game. New training samples...
Transfer learning is a new learning paradigm, in which, besides the training data for the targeted learning task, data that are related to the task (often under a different distribution) are also employed to help train a better learner. For example, out-dated data can be used as such related data. In this paper, we propose a new transfer learning framework for training neural network (NN) ensembles...
This work explores the possibility of improving the performance of Real Adaboost ensemble classifiers by replacing their standard linear combination of learners by a gating scheme. This more powerful fusion method is defined following the epoch-by-epoch construction of boosting ensembles. Preliminary experimental results support the potential of this new approach.
This paper deals with the Fault Detection and Diagnosis of steam boiler using developed artificial Neural networks model. Water low level trip of steam boiler is artificially monitored and analyzed in this study, using two different interpretation algorithms. The Broyden-Fletcher-Goldfarb-Shanno quasi-Newton and Levenberg-Marquart are adopted as training algorithms of the developed neural network...
Artificial neural networks play an important role in robot programming by demonstration. In this paper we present a method for artificial neural network training. The main idea of this method is to train the artificial neural network with all of the data, before the current training step, and at a certain step the network is already trained a huge number of times. Some features of the quality of neural...
A novel neural network with chaotic property is proposed. The network is composed by different neurons. Some activation function is chaotic iterative function instead of the conventional Sigmoid function. In the process of learning, taking advantage of the randomicity property and ergodicity property of chaos, the generalization capability and the optimizing efficiency can be improved. The simulation...
In this paper, a novel condition monitoring method of equipment based on extension neural network (ENN) is proposed. Firstly, this paper introduces the central ideas of extension theory. Then it presents the extension theory neural, including its structure and learning algorithm. In the end of the paper, the reduction gearbox of a certain equipment is researched and the extension neural network is...
The parameters of deep mine roadway surrounding rock are very important to the design, construction and stability analysis of the mine roadways. Now there are some shortcomings in the methods to obtain them. It is believed that displacement back analysis method can solve the problems, but there are some defects in it. Aiming at these problems, the paper builds a network of intelligent displacement...
In this paper, second order algorithms, such as Levenberg Marquardt algorithm, are recommended for neural network training. Being different from traditional computation in second order algorithms, the proposed method simplifies Hessian matrix computation, by removing Jacobian matrix computation and storage. Matrix multiplications are replaced by vector operations. The proposed computation not only...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.