The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
The advancements of technology continuously rising over the years has seen many applications that are useful in providing users with sufficient information to make better journey plans on their own. However, commuters still find themselves going through congested routes every day to get to their destinations. This paper attempts to delineate the possibilities of improving urban mobility through big...
For deep learning applications, large numbers of samples are essential. If this condition is not met, effective features cannot be generated and overfitting occurs especially for the small datasets such as in medical applications. To address this issue, we propose a new dynamic ensemble merging algorithm that iteratively adjusts the weights of a convolutional neural network (CNN) ensemble's elements...
In this work, we exploit a novel algorithm for capturing the Lie group manifold structure of the visual impression. By developing the single-layer Lie group model, we show how the representation learning algorithm can be stacked to yield a deep architecture. In addition, we design a Lie group based gradient descent algorithm to solve the learning problem of network weights. We show that our proposed...
In this article, we develop two visual impression models: recognition model and generalization model to simulate the cognition process of human visual systems. We show how the visual impression learned with a deep neural network can be efficiently transferred to other visual recognition tasks. By reusing the hidden layers trained in an unsupervised way, we show that we can largely reduce the number...
We present in this paper a novel approach for training a topological deep neural network with visual impression. We show that by combing denoising auto-encoder model and contractive auto-encoder with Hessian regularization model, we can achieve a deterministic auto-encoder aiming for robustness to small variations of the input. We exploit the tangent propagation algorithm to show how our algorithm...
Indoor object recognition is a key task for mobile robot indoor navigation. In this paper, we proposed a pipeline for indoor object detection based on convolutional neural network (CNN). With the proposed method, we first pre-train an off-line CNN model by using both public Indoor Dataset and private frames of videos (FoV) dataset. This is then followed by a selective search process to extract a region...
In the interest of recent accomplishments in the development of deep convolutional neural networks (CNNs) for face detection and recognition tasks, a new deep learning based face recognition attendance system is proposed in this paper. The entire process of developing a face recognition model is described in detail. This model is composed of several essential steps developed using today's most advanced...
Multimodal biometrie systems seek to alleviate some of the limitations of unimodal biometrie systems by combining multiple pieces of evidence of the same person in the deeision-making process. In this paper, a novel multimodal biometric identification system is proposed based on fusing the results obtained from both the face and the left and right irises using deep learning approaches. Firstly, the...
Automatic segmentation of the left ventricle (LV) can become a useful tool in echocardiography. Deep convolutional neural networks (CNNs) have shown promising results for image classification and segmentation on several domains, however CNNs seem to require a lot of training data. In this work, CNNs are investigated for LV ultrasound image segmentation. We study if the need for manual annotation can...
In this work, we conduct a systematic exploration on the promise and challenges of deep learning for the sparse matrix format selection. We propose a set of novel techniques to solve special challenges to deep learning, including input matrix representations, a late-merging deep neural network structure design, and the use of transfer learning to alleviate cross-architecture portability issues.
Convolutive Non-Negative Matrix Factorization model factorizes a given audio spectrogram using frequency templates with a temporal dimension. In this paper, we present a convolutional auto-encoder model that acts as a neural network alternative to convolutive NMF. Using the modeling flexibility granted by neural networks, we also explore the idea of using a Recurrent Neural Network in the encoder...
The paper presents an approach to localize human body joints in 3D coordinates based on a single low resolution depth image. First a framework to generate a database of 80k realistic depth images from a 3D body model is described. Then data preprocessing and normalization procedure, and DNN and MLP artificial neural networks architectures and training are presented. The robustness against camera distance...
Generating photo-realistic images from multiple style sketches is one of challenging tasks in image synthesis with important applications such as facial composite for suspects. While machine learning techniques have been applied for solving this problem, the requirement of collecting sketch and face photo image pairs would limit the use of the learned model for rendering sketches of different styles...
Study of critical transitions and early warning measures are of great importance for dealing with any complex system. Manually selected statistical features with handpicked parameters have been used in a wide variety of fields for this purpose. We envision the use of deep learning architectures like simple feed forward networks (FFN), convolutional neural networks (CNN) and long short-term memory...
Cardiac function is of paramount importance for both prognosis and treatment of different pathologies such as mitral regurgitation, ischemia, dyssynchrony and myocarditis. Cardiac behavior is determined by structural and functional features. In both cases, the analysis of medical imaging studies requires to detect and segment the myocardium. Nowadays, magnetic resonance imaging (MRI) is one of the...
Some of the best current face recognition approaches use feature extraction techniques based on either Principle Component Analysis (PCA), Local Binary Patterns (LBP), Autoencoder (non-linear PCA), etc. While each of these feature techniques works fairly well, we propose to combine multiple feature extractors with deep learning in a system so that the overall face recognition accuracy can be improved...
Demand is mounting in the industry for scalable GPU-based deep learning systems. Unfortunately, existing training applications built atop popular deep learning frameworks, including Caffe, Theano, and Torch, etc, are incapable of conducting distributed GPU training over large-scale clusters.To remedy such a situation, this paper presents Nexus, a platform that allows existing deep learning frameworks...
A promising direction in deep learning research is to learn representations and simultaneously discover cluster structure in unlabeled data by optimizing a discriminative loss function. Contrary to supervised deep learning, this line of research is in its infancy and the design and optimization of a suitable loss function with the aim of training deep neural networks for clustering is still an open...
Cross-resolution face recognition tackles the problem of matching face images with different resolutions. Although state-of-the-art convolutional neural network (CNN) based methods have reported promising performances on standard face recognition problems, such models cannot sufficiently describe images with resolution different from those seen during training, and thus cannot solve the above task...
Traditional domain adaptation methods attempted to learn the shared representation for distribution matching between source domain and target domain where the individual information in both domains was not characterized. Such a solution suffers from the mixing problem of individual information with the shared features which considerably constrains the performance for domain adaptation. To relax this...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.