The goal of this paper is to automatically recognize characters in popular TV series. In contrast to conventional approaches which rely on weak supervision afforded by transcripts, subtitles or character facial data, ...
详细信息
ISBN:
(纸本)9783030057107;9783030057091
The goal of this paper is to automatically recognize characters in popular TV series. In contrast to conventional approaches which rely on weak supervision afforded by transcripts, subtitles or character facial data, we formulate the problem as the multi-label classification which requires only label-level supervision. We propose a novel semantic projection network consisting of two stacked subnetworks with specially designed constraints. The first subnetwork is a contractive autoencoder which focuses on reconstructing feature activations extracted from a pre-trained single-label convolutional neural network (CNN). The second subnetwork functions as a region-based multi-label classifier which produces character labels for the input video frame as well as reconstructing the input visual feature from the mapped semantic labels space. Extensive experiments show that the proposed model achieves state-of-the-art performance in comparison with recent approaches on three challenging TV series datasets (the Big Bang Theory, the Defenders and Nirvava in Fire).
The effectiveness of learning in massive open online courses (MOOCs) can be significantly enhanced by introducing personalized intervention schemes which rely on building predictive models of student learning behavior...
详细信息
ISBN:
(纸本)9781450362566
The effectiveness of learning in massive open online courses (MOOCs) can be significantly enhanced by introducing personalized intervention schemes which rely on building predictive models of student learning behaviors such as some engagement or performance indicators. A major challenge that has to be addressed when building such models is to design handcrafted features that are effective for the prediction task at hand. In this paper, we make the first attempt to solve the feature learning problem by taking the unsupervised learning approach to learn a compact representation of the raw features with a large degree of redundancy. Specifically, in order to capture the underlying learning patterns in the content domain and the temporal nature of the clickstream data, we train a modified auto-encoder (AE) combined with the long short-term memory (LSTM) network to obtain a fixed-length embedding for each input sequence. When compared with the original features, the new features that correspond to the embedding obtained by the modified LSTM-AE are not only more parsimonious but also more discriminative for our prediction task. Using simple supervised learning models, the learned features can improve the prediction accuracy by up to 17% compared with the supervised neural networks and reduce overfitting to the dominant low-performing group of students, specifically in the task of predicting students' performance. Our approach is generic in the sense that it is not restricted to a specific supervised learning model nor a specific prediction task for MOOC learning analytics.
The idea of end-to-end learning of communication systems through neural network (NN)-based autoencoders has the shortcoming that it requires a differentiable channel model. We present in this paper a novel learning al...
详细信息
The idea of end-to-end learning of communication systems through neural network (NN)-based autoencoders has the shortcoming that it requires a differentiable channel model. We present in this paper a novel learning algorithm which alleviates this problem. The algorithm enables training of communication systems with an unknown channel model or with non-differentiable components. It iterates between training of the receiver using the true gradient, and training of the transmitter using an approximation of the gradient. We show that this approach works as well as model-based training for a variety of channels and tasks. Moreover, we demonstrate the algorithm's practical viability through hardware implementation on software defined radios (SDRs) where it achieves state-of-the-art performance over a coaxial cable and wireless channel.
Deep learning (DL) based autoencoder is a potential architecture to implement end-to-end communication systems. In this paper, we first give a brief introduction to the autoencoder-represented communication system. Th...
详细信息
ISBN:
(纸本)9781728112206
Deep learning (DL) based autoencoder is a potential architecture to implement end-to-end communication systems. In this paper, we first give a brief introduction to the autoencoder-represented communication system. Then, we propose a novel generalized data representation (GDR) to improve the data rate of DL-based communication systems. Finally, simulation results show that the proposed GDR scheme has lower training complexity, comparable block error rate performance and higher channel capacity than the conventional one-hot vector scheme. Furthermore, we investigate the effect of signal-to-noise ratio (SNR) in DL-based communication systems and show that training at high SNR can produce a good training convergence performance for the autoencoder.
We explore the usage of deep convolutional neural network for clustering the time steps of a spatial-temporal scientific dataset. Our approach first takes the scientific datasel as training data and trains a deep conv...
详细信息
ISBN:
(纸本)9781728108582
We explore the usage of deep convolutional neural network for clustering the time steps of a spatial-temporal scientific dataset. Our approach first takes the scientific datasel as training data and trains a deep convolutional autoencoder. A low-dimensional feature space or latent space can be extracted by inferencing the encoding part of the network. As a result, each time step is transformed into a feature descriptor that can be compared with each other in the feature space. In this way, we can cluster time steps according to their feature descriptors, and each group of time steps has a similar characterization. We demonstrate the effectiveness of our approach using a real-world simulation dataset of water contamination. Multiple variables and their combinations of this dataset are fed into our approach. The trained network enables the clustering of the time steps and facilitates scientists to examine their large spatial-temporal datasets.
In this paper, we utilize weight gradients from backpropagation to characterize the representation space learned by deep learning algorithms. We demonstrate the utility of such gradients in applications including perc...
详细信息
ISBN:
(纸本)9781538662496
In this paper, we utilize weight gradients from backpropagation to characterize the representation space learned by deep learning algorithms. We demonstrate the utility of such gradients in applications including perceptual image quality assessment and out-of-distribution classification. The applications are chosen to validate the effectiveness of gradients as features when the test image distribution is distorted from the train image distribution. In both applications, the proposed gradient based features outperform activation features. In image quality assessment, the proposed approach is compared with other state of the art approaches and is generally the top performing method on TID 2013 and MULTI-LIVE databases in terms of accuracy, consistency, linearity, and monotonic behavior. Finally, we analyze the effect of regularization on gradients using CURE-TSR dataset for out-of-distribution classification.
Advanced measurement techniques such as genomics are capable of acquiring high-throughput data in high dimensions, enabling new scientific discoveries, and offering unique insights in biomedical research. However, bio...
详细信息
ISBN:
(纸本)9781728118673
Advanced measurement techniques such as genomics are capable of acquiring high-throughput data in high dimensions, enabling new scientific discoveries, and offering unique insights in biomedical research. However, biological measurements can be easily affected by systematic variations especially when those measures are obtained from distinct batches involving different platforms and experimental conditions. Such batch effect is usually larger than biological signal of interest and can cause invalid downstream analysis and false discovery if not properly handled. Here we proposed a new learning approach based on multivariate distribution matching in the latent space for batch effect removal while preserving signals of most interest. This new data-driven approach consists of three key components: an autoencoder trained to encode the data into low-dimension neurons that represent data pattern;a similarity measurement procedure to identify batch-effect associated neurons;and a residual network-based matching framework to transform the affected neurons' distribution from one batch to another where the adjusted neurons will be decoded to reconstruct new datasets with batch effect removed. The effectiveness of the proposed approach has been validated in several ways using public genomic data on Alzheimer disease. This new method provides a highly promising tool for complex batch-effect adjustment and outperforms other commonly used methods.
Electrical Impedance Tomography is considered to be an alternative substitution to CT and MRI technologies as it is a non-invasive, safe medical imaging technology, and free of ionizing or heating radiation. Similar t...
详细信息
ISBN:
(纸本)9781509006175
Electrical Impedance Tomography is considered to be an alternative substitution to CT and MRI technologies as it is a non-invasive, safe medical imaging technology, and free of ionizing or heating radiation. Similar to CT and MRI technologies, reconstructing a two-dimensional EIT image is also considered an ill-posed and non-linear inverse problem, where the image quality is highly sensitive to the measurement data, and often random noise artifacts appear in the image with the different non-linear algorithms. Therefore, in this work, we have proposed a new EIT image reconstruction algorithm based on the convolution denoising autoencoder (CDAE) deep learning algorithm. Our EIT-CDAE used a convolutional neural network in the encoder and decoder network. From our experimental data using phantom data, our EIT-CDAE model has reconstructed a better EIT image quality, removing any noise artifacts, making it more robust compared to the conventional stacked autoencoder and traditional non-linear algorithms. The source code is available in the github: https://***/yongfu-li/eit-cdae-algorithm
As more and more single-cell RNA-seq (scRNA-seq) datasets become available, carrying out compare between them is key. However, this task is challengeable due to differences caused by different experiment. We proposed ...
详细信息
ISBN:
(纸本)9781728118673
As more and more single-cell RNA-seq (scRNA-seq) datasets become available, carrying out compare between them is key. However, this task is challengeable due to differences caused by different experiment. We proposed a single cell alignment method using deep autoencoder followed by k-nearst-neighbor cells (scadKNN), which learns the feature representation of the data while eliminating batch effects and dropouts through deep autoencoder and uses the low-dimensional feature to align cell types, thereby reducing calculation effort and improving alignment accuracy. Experiments using different real datasets are employed to showcase the effectiveness of the proposed approach.
Deep Learning has been very successful in many application domains. However, its usefulness in the context of network intrusion detection has not been systematically investigated. In this paper, we report a case study...
详细信息
ISBN:
(纸本)9781728142807
Deep Learning has been very successful in many application domains. However, its usefulness in the context of network intrusion detection has not been systematically investigated. In this paper, we report a case study on using deep learning for both supervised network intrusion detection and unsupervised network anomaly detection. We show that Deep Neural Networks (DNNs) can outperform other machine learning based intrusion detection systems, while being robust in the presence of dynamic IP addresses. We also show that autoencoders can be effective for network anomaly detection.
暂无评论