The Cherenkov Telescope Array (CTA) will be the world39;s leading ground-based gamma-ray observatory allowing us to study very high energy phenomena in the Universe. CTA will produce huge data sets, of the order of ...
详细信息
ISBN:
(纸本)9783319999784;9783319999777
The Cherenkov Telescope Array (CTA) will be the world's leading ground-based gamma-ray observatory allowing us to study very high energy phenomena in the Universe. CTA will produce huge data sets, of the order of petabytes, and the challenge is to find better alternative data analysis methods to the already existing ones. Machine learning algorithms, like deep learning techniques, give encouraging results in this direction. In particular, convolutional neural network methods on images have proven to be effective in patternrecognition and produce data representations which can achieve satisfactory predictions. We test the use of convolutional neuralnetworks to discriminate signal from background images with high rejections factors and to provide reconstruction parameters from gamma-ray events. The networks are trained and evaluated on artificial data sets of images. The results show that neuralnetworks trained with simulated data can be useful to extract gamma-ray information. Such networks would help us to make the best use of large quantities of real data coming in the next decades.
Unsupervised estimation of probability density functions by means of parametric mixture densities (e.g., Gaussian mixture models) may improve significantly over plain, single-density estimators in terms of modeling ca...
详细信息
ISBN:
(纸本)9783319999784;9783319999777
Unsupervised estimation of probability density functions by means of parametric mixture densities (e.g., Gaussian mixture models) may improve significantly over plain, single-density estimators in terms of modeling capabilities. Moreover, mixture densities (and even mixtures of mixture densities) may be exploited for the statistical description of phenomena whose data distributions implicitly depend on the distinct outcomes of a number of non-observable, latent states of nature. In spite of some recent advances in density estimation via neuralnetworks, no proper mixtures of neural component densities have been investigated so far. The paper proposes a first algorithm for estimating neural Mixture Densities based on the usual maximum-likelihood criterion, satisfying numerically a combination of hard and soft constraints aimed at ensuring a proper probabilistic interpretation of the resulting model. Preliminary results are presented and their statistical significance is assessed, corroborating the soundness of the approach with respect to established statistical techniques.
One of the important properties of hidden Markov models is the ability to model sequential dependencies. In this study the applicability of hidden Markov models for emotion recognition in image sequences is investigat...
详细信息
ISBN:
(纸本)9783642121586
One of the important properties of hidden Markov models is the ability to model sequential dependencies. In this study the applicability of hidden Markov models for emotion recognition in image sequences is investigated, i.e. the temporal aspects of facial expressions. The underlying image sequences were taken from the Cohn-Kanade database. Three different features (principal component analysis, orientation histograms and optical flow estimation) from four facial regions of interest (face, mouth, right and left eye) were extracted. The resulting twelve paired combinations of feature and region were used to evaluate hidden Markov models. The best single model with features of principal component analysis in the region face achieved a detection rate of 76.4 %. To improve these results further, two different fusion approaches were evaluated. Thus, the best fusion detection rate in this study was 86.1 %.
Class imbalance in machine learning is a problem often found with real-world data, where data from one class clearly dominates the dataset. Most neural network classifiers fail to learn to classify such datasets corre...
详细信息
ISBN:
(纸本)9783319461823;9783319461816
Class imbalance in machine learning is a problem often found with real-world data, where data from one class clearly dominates the dataset. Most neural network classifiers fail to learn to classify such datasets correctly if class-to-class separability is poor due to a strong bias towards the majority class. In this paper we present an algorithmic solution, integrating different methods into a novel approach using a class-to-class separability score, to increase performance on poorly separable, imbalanced datasets using Cost Sensitive neuralnetworks. We compare different cost functions and methods that can be used for training Convolutional neuralnetworks on a highly imbalanced dataset of multi-channel time series data. Results show that, despite being imbalanced and poorly separable, performance metrics such as G-Mean as high as 92.8% could be reached by using cost sensitive Convolutional neuralnetworks to detect patterns and correctly classify time series from 3 different datasets.
Several real-world problems (e.g., in bioinformatics/proteomics, or in recognition of video sequences) can be described as classification tasks over sequences of structured data, i.e. sequences of graphs, in a natural...
详细信息
ISBN:
(纸本)9783642121586
Several real-world problems (e.g., in bioinformatics/proteomics, or in recognition of video sequences) can be described as classification tasks over sequences of structured data, i.e. sequences of graphs, in a natural way. This paper presents a novel machine that can learn and carry out decision-making over sequences of graphical data. The machine involves a hidden Markov model whose state-emission probabilities are defined over graphs. This is realized by combining recursive encoding networks and constrained radial basis function networks. A global optimization algorithm which regards to the machine as a unity (instead of a bare superposition of separate modules) is introduced, via gradient-ascent over the maximum-likelihood criterion within a Baum-Welch-like forward-backward procedure. To the best of our knowledge, this is the first machine learning approach capable of processing sequences of graphs without the need of a pre-processing step. Preliminary results are reported.
The Multiple Classifier Systems are nowadays one of the most promising directions in patternrecognition. There are many methods of decision making by the ensemble of classifiers. The most popular are methods that hav...
详细信息
ISBN:
(纸本)9783540876557
The Multiple Classifier Systems are nowadays one of the most promising directions in patternrecognition. There are many methods of decision making by the ensemble of classifiers. The most popular are methods that have their origin in voting method, where the decision of the common classifier is a combination of individual classifiers' decisions. This work presents methods of classifier combination, where neuralnetworks plays a role of fuser block. Fusion on level of recognizer responses or values of their discriminant functions is applied. The qualities of proposed methods are evaluated via computer experiments on generated data and two benchmark databases.
The automatic extraction of the notes that were played in a digital musical signal (automatic music transcription) is an open problem. A number of techniques have been applied to solve it without concluding results. T...
详细信息
The automatic extraction of the notes that were played in a digital musical signal (automatic music transcription) is an open problem. A number of techniques have been applied to solve it without concluding results. The monotimbral polyphonic version of the problem is posed here: a single instrument has been played and more than one note can sound at the same time. This work tries to approach it through the identification of the pattern of a given instrument in the frequency domain. This is achieved using time-delay neuralnetworks that are fed with the band-grouped spectrogram of a polyphonic monotimbral music recording. The use of a learning scheme based on examples like neuralnetworks permits our system to avoid the use of an auditory model to approach this problem. A number of issues have to be faced to have a robust and powerful system, but promising results using synthesized instruments are presented. (c) 2005 Elsevier B.V. All rights reserved.
The existence of adversarial attacks on convolutional neuralnetworks (CNN) questions the fitness of such models for serious applications. The attacks manipulate an input image such that misclassification is evoked wh...
详细信息
ISBN:
(纸本)9783319999784;9783319999777
The existence of adversarial attacks on convolutional neuralnetworks (CNN) questions the fitness of such models for serious applications. The attacks manipulate an input image such that misclassification is evoked while still looking normal to a human observer-they are thus not easily detectable. In a different context, backpropagated activations of CNN hidden layers-"feature responses" to a given input-have been helpful to visualize for a human "debugger" what the CNN "looks at" while computing its output. In this work, we propose a novel detection method for adversarial examples to prevent attacks. We do so by tracking adversarial perturbations in feature responses, allowing for automatic detection using average local spatial entropy. The method does not alter the original network architecture and is fully human-interpretable. Experiments confirm the validity of our approach for state-of-the-art attacks on large-scale models trained on ImageNet.
Emotion recognition is a relevant task in human-computer interaction. Several patternrecognition and machine learning techniques have been applied so far in order to assign input audio and/or video sequences to speci...
详细信息
ISBN:
(纸本)9783642121586
Emotion recognition is a relevant task in human-computer interaction. Several patternrecognition and machine learning techniques have been applied so far in order to assign input audio and/or video sequences to specific emotional classes. This paper introduces a novel approach to the problem, suitable also to more generic sequence recognition tasks. The approach relies on the combination of the recurrent reservoir of an echo state network with a connectionist density estimation module. The reservoir realizes an encoding of the input sequences into a fixed-dimensionality pattern of neuron activations. The density estimator, consisting of a constrained radial basis functions network, evaluates the likelihood of the echo state given the input. Unsupervised training is accomplished within a maximum-likelihood framework. The architecture can then be used for estimating class-conditional probabilities in order to carry out emotion classification within a Bayesian setup. Preliminary experiments in emotion recognition from speech signals from the WaSeP (c) dataset show that the proposed approach is effective, and it may outperform state-of-the-art classifiers.
Transposons are segments of DNA that are capable of moving from one location to another within the genome of a cell. Understanding transposon insertion-site preferences is critically important in functional genomics a...
详细信息
暂无评论