Meta-learning consists in learning learning algorithms. We use a Long Short Term Memory (LSTM) based network to learn to compute on-line updates of the parameters of another neural network. These parameters are stored in the cell state of the LSTM. Our framework allows to compare learned algorithms to hand-made algorithms within the traditional train and test methodology. In an experiment, we l...

in this paper an application of cellular learning automata (cla) to vlsi placement is presented. the cla, which is introduced for the first time in this paper, is different from standard cellular learning automata in two respects. it has input and the cell neighborhood varies during the operation of cla. the proposed cla based algorithm for vlsi placement is tested on number of placement proble...

every year, with regard to rapid development of data, grid computing that is a kind of distributed computing system is that it has attracted the attention of most people and considerably taken into account. computing that cannot be done by huge computers can be performed by grid computing. if load balance is used, efficiency will increase in grid. resources have an important and effective role ...

We propose a simple unsupervised approach to detecting non-compositional components in multiword expressions based on Wiktionary. The approach makes use of the definitions, synonyms and translations in Wiktionary, and is applicable to any type of MWE in any language, assuming the MWE is contained in Wiktionary. Our experiments show that the proposed approach achieves higher F-score than state-o...

This paper presents a hybrid data mining approach based on supervised learning and unsupervised learning to identify the closest data patterns in the data base. This technique enables to achieve the maximum accuracy rate with minimal complexity. The proposed algorithm is compared with traditional clustering and classification algorithm and it is also implemented with multidimensional datasets. ...

This paper investigates the computational grounding of learning theories developed within a metrical phonology approach to stress assignment. In current research, the Principles and Parameters approach to learning stress is pervasive. We point out some inherent problems associated with this approach in learning the stress system of a particular language by setting parameters (the case of Dutch)...

This paper describes a genetic algorithm based learning Multiple-Value Logic (MVL) network. The proposed learning network operates on a population of candidate window parameters to produce new window parameters with lower errors between the desired outputs and the actual outputs of the MVL network. Thus, the learning MVL network has a large number of search points, making it possible to obtain ...

We present a heuristic meta-learning search method for finding a set of optimized algorithmic parameters for a range of machine learning algorithms. The method, wrapped progressive sampling, is a combination of classifier wrapping and progressive sampling of training data. A series of experiments on UCI benchmark data sets with nominal features, and five machine learning algorithms to which sim...

In most Reinforcment Learning approches, the metaparameters such as learning rate and ”temperatur” for exploration are adjusted manually. In order to build fully autonomous learning agents, it is important to develop methods for adjusting these parameters to match the demands of the task and the environment. In this paper, we propose a new method to determine the values of meta parameters in re...

Genetic algorithms (GAs) are routinely used to search problem spaces of interest. A lesser known but growing group of applications of GAs is the modeling of so-called ‘‘evolutionary processes’’, for example, organizational learning and group decision-making. Given such an application, we show it is possible to compute the likely GA parameter settings given observed populations of such an evolut...