Search results for " learning"

Improving the Competency of Classifiers through Data Generation

2001

This paper describes a hybrid approach in which sub-symbolic neural networks and symbolic machine learning algorithms are grouped into an ensemble of classifiers. Initially each classifier determines which portion of the data it is most competent in. The competency information is used to generated new data that are used for further training and prediction. The application of this approach in a difficult to learn domain shows an increase in the predictive power, in terms of the accuracy and level of competency of both the ensemble and the component classifiers.

Neural network prediction in a system for optimizing simulations

2002

Neural networks have been widely used for both prediction and classification. Back-propagation is commonly used for training neural networks, although the limitations associated with this technique are well documented. Global search techniques such as simulated annealing, genetic algorithms and tabu search have also been used for this purpose. The developers of these training methods, however, have focused on accuracy rather than training speed in order to assess the merit of new proposals. While speed is not important in settings where training can be done off-line, the situation changes when the neural network must be trained and used on-line. This is the situation when a neural network i…

ConvLSTM Neural Networks for seismic event prediction in Chile

2021

Predicting seismic risk is a challenging task in order to avoid catastrophic effects. In this work, two models based on Convolutional Network (CNN) and Long Short Term Memory (LSTM) networks are proposed to predict the seismic risk in Chile. In particular, a ConvLSTM and a Multi-column ConvLSTM network are used for the prediction of the average number of seismic events greater than 2,8 magnitude on the Richter scale, in the Chilean regions of Coquimbo and Araucania between the years 2010 and 2017. For this model, the values of the intensity function estimated through an ETAS model and the accumulated displacement prior to a the seismic events are used as inputs. In particular, given the spa…

An Encrypted Traffic Classification Framework Based on Convolutional Neural Networks and Stacked Autoencoders

2020

In recent years, deep learning-based encrypted traffic classification has proven to be effective; especially, using neural networks to extract features from raw traffic to classify encrypted traffic. However, most of the neural networks need a fixed-sized input, so that the raw traffic need to be trimmed. This will cause the loss of some information; for example, we do not know the number of packets in a session. To solve these problems, a framework, which implements both a convolutional neural network (CNN) and a stacked autoencoder (SAE), is proposed in this paper. This framework uses a CNN to extract high-level features from raw network traffic and uses an SAE to encode the 26 statistica…

Classification of Satellite Images with Regularized AdaBoosting of RBF Neural Networks

2008

A Memetic-Neural Approach to Discover Resources in P2P Networks

2008

This chapter proposes a neural network based approach for solving the resource discovery problem in Peer to Peer (P2P) networks and an Adaptive Global Local Memetic Algorithm (AGLMA) for performing in training of the neural network. The neural network, which is a multi-layer perceptron neural network, allows the P2P nodes to efficiently locate resources desired by the user. The necessity of testing the network in various working conditions, aiming to obtain a robust neural network, introduces noise in the objective function. The AGLMA is a memetic algorithm which employs two local search algorithms adaptively activated by an evolutionary framework. These local searchers, having different fe…

Two-level branch prediction using neural networks

2003

Dynamic branch prediction in high-performance processors is a specific instance of a general time series prediction problem that occurs in many areas of science. Most branch prediction research focuses on two-level adaptive branch prediction techniques, a very specific solution to the branch prediction problem. An alternative approach is to look to other application areas and fields for novel solutions to the problem. In this paper, we examine the application of neural networks to dynamic branch prediction. We retain the first level history register of conventional two-level predictors and replace the second level PHT with a neural network. Two neural networks are considered: a learning vec…

Recent advances in machine learning for maximal oxygen uptake (VO2 max) prediction : A review

2022

Maximal oxygen uptake (VO2 max) is the maximum amount of oxygen attainable by a person during exercise. VO2 max is used in different domains including sports and medical sciences and is usually measured during an incremental treadmill or cycle ergometer test. The drawback of directly measuring VO2 max using the maximal test is that it is expensive and requires a fixed and controlled protocol. During the last decade, various machine learning models have been developed for VO2 max prediction and numerous studies have attempted to predict VO2 max using data from submaximal and non-exercise tests. This article gives an overview of the machine learning models developed over the past five years (…

Understanding social behavior evolutions through agent-based modeling

2012

Agent-based social simulation as a computational approach to social simulation has been largely used to explore social phenomena. The purpose of this paper is to describe a theoretical model of transmission and evolution of social behaviors in a network of artificial societies (artificial world) using agent-based modeling technology. In this model, each agent (society) is subdivided into social behaviors where individual and social learning occur. The agent-agent interactions are carried out by their social behaviors; otherwise the agent-environment interactions through consumption of ecological resources by its social behaviors in repression and satisfaction. We distinguish social behavior…

The effectiveness of compositional animation design: Evidence from eye tracking

2017

Communication donnée le 1er septembre 2017 lors du symposium : Eye tracking as a method in learning and testing with different representations(session L 8); International audience; Learners have difficulty in decomposing conventionally designed animations to obtain raw material suitable for building high quality mental models. A composition approach to designing animations based on the Animation Processing Model was developed as a principled alternative to prevailing approaches. It provides learners with pre-decomposed material that is structured and sequenced to facilitate the relation building required for effective mental model construction. Study of a compositional animation that presen…