Auto-encoder based dimensionality reduction

Heart disease is a malignant threat to human health. Electrocardiogram (ECG) tests are used to help diagnose heart disease by recording the heart’s activity. However, automated medical-aided diagnosis with computers usually requires a large volume of labeled clinical data without patients' privacy to train the model, which is an empirical problem that still needs to be solved. To address this problem, we propose a generative adversarial network (GAN), which is composed of a bidirectional long short-term memory(LSTM) and convolutional neural network(CNN), referred as BiLSTM-CNN,to generate synthetic ECG data that agree with existing clinical data so that the features of patients with heart disease can be retained. The model includes a generator and a discriminator, where the generator employs the two layers of the BiLSTM networks and the discriminator is based on convolutional neural networks. The 48 ECG records from individuals of the MIT-BIH database were used to train the model. We compared the performance of our model with two other generative models, the recurrent neural network autoencoder(RNN-AE) and the recurrent neural network variational autoencoder (RNN-VAE). The results showed that the loss function of our model converged to zero the fastest. We also evaluated the loss of the discriminator of GANs with different combinations of generator and discriminator. The results indicated that BiLSTM-CNN GAN could generate ECG data with high morphological similarity to real ECG recordings.

/pdf/electrocardiogram-generation-with-a-bidirectional-lstm-cnn-2toolbk7an.pdf

Electrocardiogram generation with a bidirectional LSTM-CNN generative adversarial network.

https://hal.archives-ouvertes.fr/hal-01858558/document

State representation learning for control: An overview.

In this paper we present a novel approach for bottom-up multi-person 3D human pose estimation from monocular RGB images. We propose to use high resolution volumetric heatmaps to model joint locations, devising a simple and effective compression method to drastically reduce the size of this representation. At the core of the proposed method lies our Volumetric Heatmap Autoencoder, a fully-convolutional network tasked with the compression of ground-truth heatmaps into a dense intermediate representation. A second model, the Code Predictor, is then trained to predict these codes, which can be decompressed at test time to re-obtain the original representation. Our experimental evaluation shows that our method performs favorably when compared to state of the art on both multi-person and single-person 3D human pose estimation datasets and, thanks to our novel compression strategy, can process full-HD images at the constant runtime of 8 fps regardless of the number of subjects in the scene. Code and models are publicly available.

/pdf/compressed-volumetric-heatmaps-for-multi-person-3d-pose-3wpca6fypq.pdf

Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimation

General purpose computation using Graphic Processing Units (GPUs) is a well-established research area focusing on high-performance computing solutions for massively parallelizable and time-consuming problems. Classical methodologies in machine learning and data mining cannot handle processing of massive and high-speed volumes of information in the context of the big data era. GPUs have successfully improved the scalability of data mining algorithms to address significantly larger dataset sizes in many application areas. The popularization of distributed computing frameworks for big data mining opens up new opportunities for transformative solutions combining GPUs and distributed frameworks. This survey analyzes current trends in the use of GPU computing for large-scale data mining, discusses GPU architecture advantages for handling volume and velocity of data, identifies limitation factors hampering the scalability of the problems, and discusses open issues and future directions.

For further resources related to this article, please visit the WIREs website.

A survey on graphic processing unit computing for large‐scale data mining

A Folded Neural Network Autoencoder for Dimensionality Reduction

The invention of deep belief network (DBN) provides a powerful tool for data modeling. The key advantage of DBN is that it is driven by training data only, which can alleviate researchers from the routine of devising explicit models or features for data with complicated distributions. However, as the dimensionality and quantity of data increase, the computing load of training a DBN increases rapidly. Prospectively, the remarkable computing power provided by modern GPU devices can reduce the training time of DBN significantly. As highly efficient computational libraries become available, it provides additional support for GPU based parallel computing. Moreover, GPU server is more affordable and accessible compared with computer cluster or supercomputer. In this paper, we implement a variant of the DBNs, called folded-DBN, on NVIDA's Tesla K20 GPU. In our simulations, two sets of database are used to train the folded-DBNs on both CPU and GPU platforms. Comparing execution time of the fine-tuning process, the GPU implementation results 7 to 11 times speedup over the CPU platform.

A fast deep learning system using GPU

In this paper, a hierarchical neural network with cascading architecture is proposed and its application to classification is analyzed. This cascading architecture consists of multiple levels of neural network structure, in which the outputs of the hidden neurons in the higher hierarchical level are treated as an equivalent input data to the input neurons at the lower hierarchical level. The final predictive result is obtained through a modified weighted majority vote scheme. In this way, it is hoped that new patterns could be learned from hidden layers at each level and thus the combination result could significantly improve the learning performance of the whole system. In simulation, a comparison experiment is carried out among our approach and two popular ensemble learning approaches, bagging and AdaBoost. Various simulation results based on synthetic data and real data demonstrate this approach can improve the classification performance.

Jing Wang

Papers

A Folded Neural Network Autoencoder for Dimensionality Reduction

A fast deep learning system using GPU

A hierarchical neural network architecture for classification