We use a quantum annealing D-Wave 2X computer to obtain solutions to NP-hard sparse coding problems. To reduce the dimensionality of the sparse coding problem to fit on the quantum D-Wave 2X hardware, we passed downsa...
详细信息
ISBN:
(纸本)9781538691700
We use a quantum annealing D-Wave 2X computer to obtain solutions to NP-hard sparse coding problems. To reduce the dimensionality of the sparse coding problem to fit on the quantum D-Wave 2X hardware, we passed downsampled MNIST images through a bottleneck autoencoder. To establish a benchmark for classification performance on this reduced dimensional data set, we built two deep convolutional neural networks (DCNNs). The first DCNN used an AlexNet-like architecture and the second a state-of-the-art residual network (RESNET) model, both implemented in TensorFlow. The two DCNNs yielded classification scores of 94.54 +/- 0.7% and 98.8 +/- 0.1%, respectively. As a control, we showed that both DCNN architectures produced near-state-of-the-art classification performance (similar to 99%) on the original MNIST images. To obtain a set of optimized features for inferring sparse representations of the reduced dimensional MNIST dataset, we imprinted on a random set of 47 image patches followed by an off-line unsupervised learning algorithm using stochastic gradient descent to optimize for sparse coding. Our single-layer of sparse coding matched the stride and patch size of the first convolutional layer of the AlexNet-like DCNN and contained 47 fully-connected features, 47 being the maximum number of dictionary elements that could be embedded onto the D-Wave 2X hardware. When the sparse representations inferred by the D-Wave 2X were passed to a linear support vector machine, we obtained a classification score of 95.68%. We found that the classification performance supported by quantum inference was maximal at an optimal level of sparsity corresponding to a critical value of the sparsity/reconstruction error trade-off parameter that previous work has associated with a second order phase transition, an observation supported by a free energy analysis of D-Wave energy states. We mimicked a transfer learning protocol by feeding the D-Wave representations into a multilayer perceptron
The use of wind energy is progressively utilized to produce electrical energy. Wind energy is related to the variation of some atmospheric variables such as wind direction, wind speed, air density and atmospheric pres...
详细信息
ISBN:
(纸本)9781728101125
The use of wind energy is progressively utilized to produce electrical energy. Wind energy is related to the variation of some atmospheric variables such as wind direction, wind speed, air density and atmospheric pressure. Recently, numerous methods base on Artificial Intelligence techniques to forecast wind speed have been proposed in the literature. In this paper a new artificial intelligence approach for wind speed time series forecasting is proposed, it is composed from two blocs: The first one is based on the use of a deep architecture. The autoencoder which is a type of deep neural networks, utilized generally for Denoising, is employed to reduce the wind speed input dimensionality. In the second bloc of the proposed methodology, the Elman neural network is employed to forecast future values of wind series, it is a kind of recurrent neural networks that are very sensitive to historical variations. To evaluate our approach we used the following error indicators: Root Mean Square Error (RMSE), Mean Absolute Bias Error (MABE), Mean Absolute Percentage Error (MAPE) and the coefficient of determination (R-2). The obtained results are compared with those of the Extreme Learning Machine method.
Designing models for learning dataset with complex distributions is one of the main challenges that still remains in machine learning areas. We propose CollaboNet, which can divide a large dataset into sub-datasets, t...
详细信息
ISBN:
(纸本)9781479970612
Designing models for learning dataset with complex distributions is one of the main challenges that still remains in machine learning areas. We propose CollaboNet, which can divide a large dataset into sub-datasets, train two generative models separately, and let two models work together to achieve better performance. The proposed algorithm divides a large dataset without label since the capability difference between two generative models in performing tasks on each data is the main criterion for dividing a large dataset. In other words, the classification model can be trained by unsupervised manner. autoencoder experiments for pure MNIST and the datasets combined artificially from two image sets shows that CollaboNet successfully splits large datasets without labels, improving the performance of generative models.
Breast cancer is the second leading cause of death for women in the U.S. Early detection of breast cancer has been shown to be the key to higher survival rates for breast cancer patients. We are investigating infrared...
详细信息
ISBN:
(纸本)9781538693063
Breast cancer is the second leading cause of death for women in the U.S. Early detection of breast cancer has been shown to be the key to higher survival rates for breast cancer patients. We are investigating infrared thermography as a noninvasive adjunctive to mammography for breast screening. Thermal imaging is safe, radiation-free, pain-free, and non-contact. Segmentation of breast area from the acquired thermal images will help limit the area for tumor search and reduce the time and effort needed for manual hand segmentation. autoencoder-like convolutional and deconvolutional neural networks (C-DCNN) are promising computational approaches to automatically segment breast areas in thermal images. In this study, we apply the C-DCNN to segment breast areas from our thermal breast images database, which we are collecting in our clinical trials by imaging breast cancer patients with our infrared camera (N2 Imager). For training the C-DCNN, the inputs are 132 gray-value thermal images and the corresponding manually-cropped breast area images (binary masks to designate the breast areas). For testing, we input thermal images to the trained C-DCNN and the output after post-processing are the binary breast-area images. Cross-validation and comparison with the ground-truth images show that the C-DCNN is a promising method to segment breast areas. The results demonstrate the capability of C-DCNN to learn essential features of breast regions and delineate them in thermal images.
Dimensionality reduction is a common method for analyzing and visualizing high-dimensional data. However, reasoning dynamically about the results of a dimensionality reduction is difficult Dimensionality-reduction alg...
详细信息
ISBN:
(纸本)9781450356206
Dimensionality reduction is a common method for analyzing and visualizing high-dimensional data. However, reasoning dynamically about the results of a dimensionality reduction is difficult Dimensionality-reduction algorithms use complex optimizations to reduce the number of dimensions of a dataset, but these new dimensions often lack a clear relation to the initial data dimensions, thus making them difficult to interpret. Here we propose a visual interaction framework to improve dimensionality-reduction based exploratory data analysis. We introduce two interaction techniques, forward projection and backward projection, for dynamically reasoning about dimensionally reduced data, We also contribute two visualization techniques, prolines and feasibility maps, to facilitate the effective use of the proposed interactions. We apply our framework to PCA and autoencoder-based dimensionality reductions. Through data-exploration examples, we demonstrate how our visual interactions can improve the use of dimensionality reduction in exploratory data analysis.
Aesthetic perception is nearly the most direct impact people could receive from images. Recent research on image understanding is mainly focused on image analysis, recognition and classification, regardless of the aes...
详细信息
ISBN:
(纸本)9781538646588
Aesthetic perception is nearly the most direct impact people could receive from images. Recent research on image understanding is mainly focused on image analysis, recognition and classification, regardless of the aesthetic meanings embedded in images. In this paper, we systematically study the problem of understanding the aesthetic styles of social images. First, we build a two-dimensional Image Aesthetic Space (IAS) to describe image aesthetic styles quantitatively and universally. Then, we propose a Bimodal Deep autoencoder with Cross Edges (BDA-CE) to deeply fuse the social image related features (i.e. images' visual features, tags' textual features). Connecting BDA-CE with a regression model, we are able to map the features to the IAS. The experimental results on the benchmark dataset we build with 120 thousand Flickr images show that our model outperforms (+ 5.5% in terms of MSE) alternative baselines. Furthermore, we conduct an interesting case study to demonstrate the advantages of our methods.
Surface defect detection and classification based on machine vision can greatly improve the efficiency of industrial production. With enough labeled images, defect detection methods based on convolution neural network...
详细信息
ISBN:
(纸本)9783319973104;9783319973098
Surface defect detection and classification based on machine vision can greatly improve the efficiency of industrial production. With enough labeled images, defect detection methods based on convolution neural network have achieved the detection effect of state-of-art. However in practical applications, the defect samples or negative samples are usually difficult to be collected beforehand and manual labelling is time-consuming. In this paper, a novel defect detection framework only based on training of positive samples is proposed. The basic detection concept is to establish a reconstruction network which can repair defect areas in the samples if they are existed, and then make a comparison between the input sample and the restored one to indicate the accurate defect areas. We combine GAN and autoencoder for defect image reconstruction and use LBP for image local contrast to detect defects. In the training process of the algorithm, only positive samples is needed, without defect samples and manual label. This paper carries out verification experiments for concentrated fabric images and the dataset of DAGM 2007. Experiments show that the proposed GAN+LBP algorithm and supervised training algorithm with sufficient training samples have fairly high detection accuracy. Because of its unsupervised characteristics, it has higher practical application value.
Signal map is of great importance, especially in the dawn of 5G network, for site spectrum monitoring, location-based services (LBS), network construction, and cellular planning. Despite its significance, the traditio...
详细信息
ISBN:
(纸本)9781728125848
Signal map is of great importance, especially in the dawn of 5G network, for site spectrum monitoring, location-based services (LBS), network construction, and cellular planning. Despite its significance, the traditional signal map construction, e.g., through full site survey, could be time-consuming and labor-intensive as the signal varies frequently over time and the accuracy requirement grows rapidly with the emergence of new applications. Even with crowdsourcing scheme, the participants tend to be unevenly distributed in space while the encouragement budgets for the participants could be far from enough to collect adequate high-quality measurements. Therefore, the signal map constructed by crowdsourcing is often sparse and incomplete. To this end, in this paper, we study how to effectively reconstruct and update the signal map in the case of partially measured signal maps with minimum cost and propose an auto-encoder-based active signal map reconstruction method (AER). Our method is mainly innovative in three parts. Firstly, AER can effectively update the signal map with only a small number of observations while also fully using the incomplete historical signals to effectively update the signal map online. Secondly, AER consists of an active query mechanism which quantitatively evaluates the most valuable measurement site for reconstruction, which further reduces the measurement cost to a large extent. Thirdly, to cope with the measurement dynamics, we give a new signal map model describing not only the signal strength but also the signal dynamics, based on which an advanced AER algorithm is proposed. The simulation results demonstrate the advantages and effectiveness of our approach in both accuracy and cost.
This paper proposes innovative anomaly detection technologies for manufacturing systems. We combine the event ordering relationship based structuring technique and the deep neural networks to develop the structured ne...
详细信息
ISBN:
(纸本)9781538673454
This paper proposes innovative anomaly detection technologies for manufacturing systems. We combine the event ordering relationship based structuring technique and the deep neural networks to develop the structured neural networks for anomaly detection. The event ordering relationship based neural network structuring process is performed before neural network training process and determines important neuron connections and weight initialization. It reduces the complexity of the neural networks and can improve anomaly detection accuracy. The structured time delay neural network (TDNN) is introduced for anomaly detection via supervised learning. To detect anomaly through unsupervised learning, we propose the structured autoencoder. The proposed structured neural networks outperform the unstructured neural networks in terms of anomaly detection accuracy and can reduce test error by 20%. Compared with popular methods such as one-class SVM, decision trees, and distance-based algorithms, our structured neural networks can reduce anomaly detection misclassification error by as much as 64%.
The exponential growth of the data collected by telescopes have turned astronomy into a data-drive science. The detection of astronomical transient events, short-lived and bright phenomena such as the Supernovae, is c...
详细信息
ISBN:
(纸本)9781509060146
The exponential growth of the data collected by telescopes have turned astronomy into a data-drive science. The detection of astronomical transient events, short-lived and bright phenomena such as the Supernovae, is currently a main science driver of many astronomical surveys. There is an opportunity for the application of machine learning methods for the automatic detection of astronomical transients. In this paper we focus on the unsupervised learning case to perform an exploratory analysis on a dataset of 1,250,000 astronomical transient candidates from the High Cadence Transient Survey. Our contributions can be summarized in 1) The application of Deep Variational Embedding for latent space clustering of a large database of transient candidates obtaining a clustering accuracy of 95:33% and 2) The proposal of an auto-regularization term as a novel approach to solve the common problem of over-regularization in variational autoencoders, we show that using this term not only improves the convergence of the algorithm but also increases the clustering accuracy and reconstruction quality.
暂无评论