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.
Stochastic gradient algorithms are the main focus of large-scale optimization problems and led to important successes in the recent advancement of the deep learning algorithms. The convergence of SGD depends on the careful choice of learning rate and the amount of the noise in stochastic estimates of the gradients. In this paper, we propose an adaptive learning rate algorithm, which utilizes stochastic...
This work addresses the task of camera localization in a known 3D scene given a single input RGB image. State-of-the-art approaches accomplish this in two steps: firstly, regressing for every pixel in the image its 3D scene coordinate and subsequently, using these coordinates to estimate the final 6D camera pose via RANSAC. To solve the first step. Random Forests (RFs) are typically used. On the other...
Tensegrity robots, composed of rigid rods connected by elastic cables, have a number of unique properties that make them appealing for use as planetary exploration rovers. However, control of tensegrity robots remains a difficult problem due to their unusual structures and complex dynamics. In this work, we show how locomotion gaits can be learned automatically using a novel extension of mirror descent...
This paper develops a method to use RGB-D cameras to track the motions of a human spinal cord injury patient undergoing spinal stimulation and physical rehabilitation. Because clinicians must remain close to the patient during training sessions, the patient is usually under permanent and transient occlusions due to the training equipment and the movements of the attending clinicians. These occlusions...
There has been a recent paradigm shift in robotics to data-driven learning for planning and control. Due to large number of experiences required for training, most of these approaches use a self-supervised paradigm: using sensors to measure success/failure. However, in most cases, these sensors provide weak supervision at best. In this work, we propose an adversarial learning framework that pits an...
The ability of autonomous mobile robots to react to and recover from potential failures of on-board systems is an important area of ongoing robotics research. With increasing emphasis on robust systems and long-term autonomy, mobile robots must be able to respond safely and intelligently to dangerous situations. Recent developments in computer vision have made autonomous vision based navigation possible...
Scene understanding is a crucial requirement for robot navigation. Conditional Random Fields (CRF) are commonly used to solve the scene labelling problem since they represent contextual information efficiently and provide efficient inference methods. However, when a robot navigates through an unknown environment, it is often necessary to adjust the parameters of the CRF online to maintain the same...
The paper presents a novel, principled approach to train recurrent neural networks from the Reservoir Computing family that are robust to missing part of the input features at prediction time. By building on the ensembling properties of Dropout regularization, we propose a methodology, named DropIn, which efficiently trains a neural model as a committee machine of subnetworks, each capable of predicting...
Deep neural networks have achieved significant success for image recognition problems. Despite the wide success, recent experiments demonstrated that neural networks are sensitive to small input perturbations, or adversarial noise. The lack of robustness is intuitively undesirable and limits neural networks applications in adversarial settings, and for image search and retrieval problems. Current...
Tracking-by-detection methods treat the target location as a classification problem in which the approach SVM + HOG shows a good performance. However, training a good SVM classifier is cost expensive. In this paper, we replace SVM by linear discriminant analysis (LDA) for classification where the mean and covariance of negative examples are evaluated only once. Not only the training is much cheaper,...
Growing number of surveillance and biometric applications seek to recognize the face of individuals appearing in the viewpoint of video cameras. Systems for video-based FR can be subjected to challenging operational environments, where the appearance of faces captured with video cameras varies significantly due to changes in pose, illumination, scale, blur, expression, occlusion, etc. In particular,...
A recent work introduced the concept of deep dictionary learning. In deep dictionary learning, the first level proceeds like standard dictionary learning; in sub-sequent layers the (scaled) output coefficients from the previous layer are used as inputs for dictionary learning. This is an unsupervised deep learning approach. The features from the final / deepest layer are employed for subsequent analysis...
Inspired by research in the deep learning community, we demonstrate the effectiveness of optimizing a deep recurrent neural network with gated recurrent unit modules to control a sophisticated and highly nonlinear flight vehicle. We present an optimization procedure that leverages ideas from Lyapunov funnels and robust nonlinear control to create a robust and high performance controller that tracks...
The ability to learn from noisy and incomplete information is highly desired in cognitive systems. When these cognitive systems are realized in hardware, such as neuromemristive systems, an added constraint is how the algorithms adapt to the inherent noise and variability from the devices. In this work, we explore the robustness of the reservoir computing algorithm, specifically a liquid state machine,...
Development of fast watermarking schemes for all multimedia objects is crucial to the present day research in information security. Besides speed of execution minimizing the trade-off between visual quality and robustness is another important requirement of this research domain. In view of this, a newly developed single layer feedforward network (SLFN) commonly known as Bidirectional Extreme Learning...
With the rapid popularity of the Internet, a large amount of new malware is produced every day, while the traditional signature based malware detection algorithm is unable to detect such unseen malware. In recent years, many machine learning based algorithms have been proposed to detect new malware, and several of these algorithms are able to achieve quite good detection performance when supplied...
The primary objective of this paper is to explore the applicability of sparse representation based classification (SRC), particularly at the fingerprint recognition problem. This paper proposes sparse proximity based fingerprint matching methodology. The sparse representation based classification problem can be solved as representing the test sample in terms of training set with some sparse residual...
Anomaly intrusion detection models play a crucial role in identifying zero day attacks that occur in the computer or networks. However they suffer from many functional issues such as high false alarm rate and low detection rate. That arises, in large part, due to manipulating huge traffic data with many outliers. To overcome that, many machine learning techniques were widely employed. This paper proposes...
Nowadays, image processing is getting more popular due to the daily increase of diverse data acquisition methods such as digital scanners and cameras. Due to the high volume of archived documents, automatic document classification methods can help to save the time and space in digital document organization. Logos in official and business documents are used to identify document identities. Different...
Retinal Neovascularization (NV) is a critical stage of Diabetic Retinopathy (DR) and its detection is important to prevent blindness. Existing fully supervised frameworks typically take a patch-based approach and report good results only on limited number of images due to sparsity of annotated data. We propose a patch-based semi-supervised framework which paves the way for including unlabeled data...
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.